System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting information on medical care by a user; means for analyzing the input information; means for generating an initial diagnosis result based on an analysis result; means for automatically generating an additional question; means for making a final diagnosis based on a user's answer; means for generating an electronic medical record based on the final diagnosis result; means for storing the generated electronic medical record and the diagnosis result; means for guiding the user to an appropriate medical institution; and means for transmitting the electronic medical record to the medical institution.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In modern society, barriers to accessing medical institutions are increasing. In particular, for people with mild symptoms, reluctance to visit a medical institution and time constraints make it difficult to receive appropriate medical treatment. Furthermore, the burden on medical professionals of conducting medical interviews and creating medical records is increasing due to factors such as an increase in the number of patients, an aging population, and the spread of infectious diseases. The present invention aims to solve these problems and provide a system that makes it easier for individuals to access appropriate medical institutions. [Means for solving the problem]

[0005] The present invention solves these problems by providing a system that includes: a means for a user to input medical information; a means for analyzing the input information; a means for generating an initial diagnosis based on the analysis results; a means for automatically generating additional questions; a means for making a final diagnosis based on the user's answers; a means for generating an electronic medical record based on the final diagnosis; a means for saving the generated electronic medical record and the diagnosis results; a means for guiding the user to an appropriate medical institution; and a means for transmitting the electronic medical record to the medical institution. The system also includes a means for updating the electronic medical record based on the user's answers and a means for automatically suggesting medical information related to the updated electronic medical record, thereby improving the accuracy and efficiency of medical treatment. Furthermore, the system includes a means for analyzing the user's input information using natural language processing technology and a means for making an initial diagnosis and a final diagnosis by applying a diagnostic algorithm, thereby automating the diagnostic process and realizing rapid and accurate medical support.

[0006] "User" refers to a person who inputs medical information and receives a diagnosis or guidance to a medical institution.

[0007] "Means for input" refers to an interface that allows a user to provide information about their symptoms and medical care to the system in the form of text, voice, or other information.

[0008] "Means for analysis" refers to the process of analyzing the received user information using natural language processing and machine learning techniques to seek an appropriate diagnosis and treatment.

[0009] "Initial diagnosis" refers to the first estimated diagnosis based on the information provided by the user.

[0010] "Means for automatically generating questions" refers to the process by which the system automatically generates questions necessary to collect additional medical information based on the initial diagnosis.

[0011] "Final diagnosis" refers to the comprehensive examination results after collecting additional information.

[0012] "Electronic Medical Record" refers to a digital record of information about a user's medical condition, diagnoses, and treatments.

[0013] "Means of storage" refers to the process for securely storing the generated electronic medical records and diagnostic results in a database, cloud storage, etc.

[0014] "Guidance means" refers to the process of suggesting appropriate medical institutions to the user and providing necessary information based on the final diagnosis results.

[0015] "Means of transmission" refers to the communication protocol or method for securely transmitting the generated electronic medical record to the selected medical institution.

[0016] "Means of updating" refers to the process of updating the contents of existing electronic medical records based on user responses and new diagnostic information.

[0017] "Automatic suggestion method" refers to the process by which the system automatically displays new medical information related to an updated electronic medical record.

[0018] "Natural language processing technology" refers to computer technology for analyzing text information entered by a user and understanding its meaning.

[0019] "Diagnostic algorithm" refers to a mathematical and logical procedure for calculating a medical diagnosis based on a user's symptoms and information. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0025] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] The present invention is a system that allows a user to input medical information, analyzes the information, and provides a diagnosis. How the system operates and how it is specifically implemented will be described below.

[0042] Main processing of the program

[0043] 1. User symptom input

[0044] Users use devices such as smartphones or computers to input medical information into the AI ​​chatbot app.

[0045] For example, a user can input "I have a sore throat and a slight fever," and this information is sent to the server via the terminal.

[0046] 2. Symptom analysis

[0047] The server analyzes the symptom information received from the terminal using natural language processing (NLP) technology.

[0048] The server extracts keywords such as "sore throat" and "fever" and applies an initial diagnostic algorithm to identify potential diagnoses.

[0049] 3. Presenting the initial diagnosis and asking follow-up questions

[0050] The server generates an initial diagnosis based on the analysis results.

[0051] If the initial diagnosis is inconclusive, the server automatically generates additional questions and displays them to the user via the terminal.

[0052] The user answers the follow-up questions and sends, for example, "Yes, I have a slight cough."

[0053] 4. Final diagnosis and medical record generation

[0054] The server re-analyzes the additional answers and determines the final diagnosis, for example, a "mild cold."

[0055] The server automatically generates and securely stores electronic medical records containing the user's medical condition and diagnosis results.

[0056] 5. Information on specialized medical institutions

[0057] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[0058] The server transmits information about appropriate medical institutions to the terminal and provides guidance to the user.

[0059] The user can visit a medical institution based on the guidance.

[0060] 6. AI medical record handover

[0061] The server securely transmits the electronic medical record to the selected medical institution.

[0062] The medical institution's terminal prepares for medical treatment based on the received electronic medical record.

[0063] This allows the user to receive medical treatment smoothly.

[0064] Specific examples

[0065] scenario

[0066] Consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[0067] 1. User symptom input

[0068] The user (Taro) launches the app and enters, "I have a sore throat and a slight fever."

[0069] The terminal transmits this input information to the server.

[0070] 2. Symptom analysis

[0071] The server uses natural language processing to extract keywords such as "sore throat" and "fever" from the received information, and considers the possibility of a cold in the initial diagnosis.

[0072] 3. Presenting the initial diagnosis and asking follow-up questions

[0073] The server generates an initial diagnosis and determines that the patient "may have a cold."

[0074] To obtain additional information, the server generates a question, "Do you have a cough or headache?", and displays it on the device.

[0075] The user (Taro) responds, "Yes, I have a slight cough."

[0076] 4. Final diagnosis and medical record generation

[0077] The server reanalyzes the additional answers and determines the final diagnosis as "a mild cold."

[0078] The server generates an electronic medical record based on the diagnosis results and stores it securely.

[0079] 5. Information on specialized medical institutions

[0080] The server selects a nearby internal medicine clinic based on the electronic medical records and diagnosis results.

[0081] The server sends information about recommended medical institutions to the terminal and displays it to Taro.

[0082] The user (Taro) makes a reservation by following the instructions.

[0083] 6. AI medical record handover

[0084] The server sends the electronic medical record to the clinic where the appointment is completed.

[0085] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[0086] In this way, the present invention provides users with prompt and appropriate medical services and improves the efficiency of medical treatment at medical institutions.

[0087] The processing flow will be explained below.

[0088] Step 1:

[0089] Users launch the smartphone application and enter their symptoms by text or voice, for example, "I have a sore throat and a fever of 37.5 degrees."

[0090] Step 2:

[0091] The terminal receives the user's input information and transmits the text data to the server.

[0092] Step 3:

[0093] The server passes the received text data to a natural language processing (NLP) module to extract symptom keywords, such as "sore throat" and "fever."

[0094] Step 4:

[0095] The server applies an initial diagnosis algorithm based on the extracted keywords to generate an initial diagnosis result, for example, determining that there is a high possibility of a cold.

[0096] Step 5:

[0097] If the initial diagnosis result does not provide sufficient definitive information, the server automatically generates additional questions, such as "Do you have a cough or headache?"

[0098] Step 6:

[0099] The terminal displays the additional questions sent from the server to the user.

[0100] Step 7:

[0101] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[0102] Step 8:

[0103] The terminal transmits the user's additional responses to the server.

[0104] Step 9:

[0105] The server re-analyzes the additional responses and makes a final diagnosis, for example, a "mild cold."

[0106] Step 10:

[0107] The server automatically generates an electronic medical record based on the user's medical condition and diagnosis results, and securely stores that information in a database.

[0108] Step 11:

[0109] The server selects an appropriate medical institution in the user's area based on the final diagnosis and the generated electronic medical record.

[0110] Step 12:

[0111] The server sends information about the selected medical institution to the terminal and provides the user with guidance, such as "The nearest internal medicine clinic is Hospital A."

[0112] Step 13:

[0113] The user checks the information about the medical institution provided by the server and makes an appointment for a medical examination.

[0114] Step 14:

[0115] The server securely transmits the user's electronic medical record to the medical institution where the user has completed an appointment.

[0116] Step 15:

[0117] The medical institution's terminal receives the electronic medical records sent from the server and prepares for treatment, ensuring smooth treatment when the patient arrives.

[0118] In this way, the system of the present invention provides a seamless process from the user's symptom input to a final diagnosis and guidance to an appropriate medical institution, thereby streamlining medical access.

[0119] Example 1

[0120] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0121] There is a need for systems that allow users to input medical information, analyze that information appropriately, and provide a fast and accurate diagnosis, as well as automate the process of directing patients to appropriate medical institutions based on the diagnosis results and the safe transfer of electronic medical records. Furthermore, because conventional systems have difficulty selecting a medical institution appropriate for the user's area and improving the accuracy of diagnosis results, new technologies are needed to improve the quality of medical services.

[0122] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0123] In this invention, the server includes means for a user to input medical information, means for analyzing the input information, means for generating an initial diagnosis based on the analysis results, means for automatically generating additional questions, means for making a final diagnosis based on the user's answers, means for generating an electronic medical record based on the final diagnosis, means for saving the generated electronic medical record and the diagnosis results, means for directing the user to an appropriate medical institution, means for transmitting the electronic medical record to the medical institution, means for selecting a medical institution suitable for the user's area based on the electronic medical record and the diagnosis results, and means for securely transmitting the electronic medical record to the selected medical institution. This allows the user to receive a quick and accurate diagnosis, and enables directing to an appropriate medical institution and handing over the diagnosis results.

[0124] 1. "User" refers to a person who inputs medical information and receives diagnosis results and guidance on medical institutions.

[0125] 2. "Means for inputting information" means a device or interface used by a user to input medical information.

[0126] 3. "Means for analyzing information" refers to a system that uses data processing technology to analyze input information, extract keywords, and perform initial diagnosis.

[0127] 4. "Means for generating an initial diagnosis" means an algorithm or process that generates a preliminary diagnosis based on the analyzed information.

[0128] 5. "Means for automatically generating additional questions" refers to a system that automatically generates questions to obtain additional information necessary to improve the accuracy of initial diagnostic results.

[0129] 6. "Means for making a final diagnosis" means a system or process that reanalyzes the user's additional responses and determines a final diagnosis.

[0130] 7. "Means for generating electronic medical records" refers to a system that automatically creates electronic medical records that record diagnostic results and the user's medical condition.

[0131] 8. "Means for storing diagnostic results" means a system that stores the generated electronic medical records and diagnostic results in secure and reliable storage.

[0132] 9. "Means for guiding users to medical institutions" refers to a system that selects a medical institution suitable for the user based on the diagnosis results and provides that information to the user.

[0133] 10. "Means for transmitting electronic medical records" means the communications process and infrastructure for securely transmitting the generated electronic medical records to the selected healthcare provider.

[0134] 11. "Means for selecting a medical institution suitable for the area" refers to a system that selects the most suitable facility from local medical institutions based on the user's location information and diagnosis results.

[0135] 12. "Means for securely transmitting electronic medical records" means a system or protocol for transmitting electronic medical records to a medical institution using security such as encrypted communications.

[0136] This invention is a system in which a user inputs medical information, analyzes that information, and provides a diagnosis. The system is basically composed of a terminal, a server, and a medical institution's terminal. Each component of the system and its specific operation are described below.

[0137] Terminal

[0138] The terminal refers to a device such as a smartphone or PC that users use to input medical information. Specifically, they perform the following operations:

[0139] The user launches the application and enters information about their symptoms or illnesses.

[0140] For example, you might type, "I have a sore throat and a slight fever." This information is sent over the internet to a server.

[0141] server

[0142] The server is the main part that analyzes the information received from the user and generates the diagnosis results. The server uses the following hardware and software:

[0143] Hardware: Server equipment equipped with a high-performance CPU, sufficient memory, SSD storage, etc.

[0144] Software: TensorFlow and Spacy for natural language processing (NLP) techniques, MySQL for database management systems (DBMS), Scikit-learn and TensorFlow for diagnostic algorithms.

[0145] The operation of the server is as follows.

[0146] The information sent from the terminal is first stored in a database.

[0147] Next, an NLP model using TensorFlow and Spacy analyzes the input information and extracts keywords such as "sore throat" and "fever."

[0148] Based on the extracted keywords, an initial diagnosis algorithm (Scikit-learn or TensorFlow) is applied to generate initial diagnosis results.

[0149] If the initial diagnosis is uncertain, the server automatically generates additional questions and sends them to the terminal.

[0150] If the user answers additional questions, the information is sent back to the server for reanalysis.

[0151] Once the final diagnosis is confirmed, an electronic medical record is automatically generated and securely stored in an AWS S3 bucket or similar.

[0152] Based on the diagnosis results and electronic medical records, the system selects a medical institution suitable for the user's area. For example, it uses the Google Maps API to search for nearby medical institutions.

[0153] Medical institution terminals

[0154] The medical institution's terminal is a device for providing medical treatment based on the received electronic medical records.

[0155] Electronic medical records sent from the server are transmitted using encryption technology such as SSL / TLS.

[0156] The medical institution's terminal receives the electronic medical record, and medical staff prepare for treatment.

[0157] Specific examples

[0158] For example, if a user experiences cold-like symptoms, the system operates as follows.

[0159] 1. User symptom input

[0160] The user launches the app and types, "I have a sore throat and a slight fever."

[0161] The terminal sends this information to the server.

[0162] 2. Symptom analysis

[0163] The server uses NLP to extract keywords such as "sore throat" and "fever" from the received information, and considers the possibility of a cold in the initial diagnosis.

[0164] 3. Presenting the initial diagnosis and asking follow-up questions

[0165] The server generates an initial diagnosis of "suspected cold."

[0166] To get additional information, the server generates a question, "Do you have a cough or headache?", and displays it on the device.

[0167] The user responds, "Yes, I have a slight cough."

[0168] 4. Final diagnosis and medical record generation

[0169] The server reanalyzes the additional answers and determines the final diagnosis as "mild cold."

[0170] The server generates an electronic medical record based on the diagnosis results and stores it securely.

[0171] 5. Information on specialized medical institutions

[0172] Based on the electronic medical records and diagnosis results, the server selects a nearby internal medicine clinic and sends the information to the terminal.

[0173] The user makes a reservation by following the instructions.

[0174] 6. AI medical record handover

[0175] The server sends the electronic medical record to the clinic where the reservation is completed.

[0176] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[0177] Example prompts to input to the generative AI model

[0178] Example 1: "Describe a program that analyzes symptom information entered by a user and selects the most appropriate medical institution."

[0179] Example 2: "Given a patient's sore throat and mild fever, detail the process of using NLP to generate an initial diagnosis and follow-up questions, and then storing the final diagnosis in the electronic medical record."

[0180] This system provides users with accurate and prompt medical services, significantly improving the efficiency of medical treatment at medical institutions.

[0181] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0182] Step 1:

[0183] User symptom input

[0184] Users use their smartphones or computers to input symptom information into the AI ​​chatbot app, such as "sore throat" and "mild fever."

[0185] Specific behavior:

[0186] The user launches the app and enters "I have a sore throat and a slight fever" into the symptom entry form.

[0187] After entering the information, press the send button.

[0188] Input: Symptom information entered by the user.

[0189] Output: The device sends the input information to the server.

[0190] Step 2:

[0191] Symptom analysis

[0192] The server receives the symptom information sent from the device and analyzes it using natural language processing (NLP) technology. Specifically, it uses TensorFlow and Spacy to extract keywords such as "sore throat" and "fever" from the text data.

[0193] Specific behavior:

[0194] The server stores the received symptom data in a database.

[0195] An NLP model analyzes the data and extracts keywords.

[0196] Input: Symptom information received by the server.

[0197] Output: Extracted keywords "sore throat" and "fever".

[0198] Step 3:

[0199] Generate an initial diagnosis

[0200] Based on the extracted keywords, the server applies an initial diagnostic algorithm (using Scikit-learn or TensorFlow) to generate provisional diagnostic results.

[0201] Specific behavior:

[0202] The server runs an algorithm to provide an initial diagnosis corresponding to the symptoms.

[0203] The initial diagnosis result is "suspected cold."

[0204] Input: Extracted keywords.

[0205] Output: Initial diagnosis: "Suspected cold."

[0206] Step 4:

[0207] Generate and present follow-up questions

[0208] If the initial diagnosis is inconclusive, the server automatically generates additional questions and presents them to the user via the terminal, who then answers the questions.

[0209] Specific behavior:

[0210] The server generates follow-up questions based on the initial diagnostic results.

[0211] An additional question, "Do you have a cough or headache?", is generated and sent to the device.

[0212] The user receives the question and responds, "Yes, I have a slight cough."

[0213] Input: Initial diagnosis and follow-up questions.

[0214] Output: User answers "Yes, I have a slight cough."

[0215] Step 5:

[0216] Confirmation of final diagnosis and creation of medical records

[0217] The server reanalyzes the user's additional answers and determines the final diagnosis, which is a "mild cold." It also automatically generates and saves an electronic medical record based on the final diagnosis.

[0218] Specific behavior:

[0219] The server re-analyzes the additional answers and applies the final diagnostic algorithm.

[0220] The final diagnosis is confirmed as "mild cold."

[0221] Generate and securely store electronic medical records.

[0222] Input: The user's additional answer.

[0223] Output: Final diagnosis and electronic medical record.

[0224] Step 6:

[0225] Guide to specialized medical institutions

[0226] Based on the final diagnosis, the server selects a medical institution suitable for the user's area and sends that information to the terminal to guide the user.

[0227] Specific behavior:

[0228] The server uses Google Maps APIs and other tools to search for nearby medical institutions based on the user's location information.

[0229] Information on the appropriate medical institution is selected and sent to the terminal.

[0230] The user checks the information and makes a reservation.

[0231] Input: Electronic medical record and final diagnosis.

[0232] Output: Information on selected medical institutions.

[0233] Step 7:

[0234] AI medical record handover

[0235] The server securely transmits the electronic medical record to the selected medical institution, and the medical institution's terminal prepares for treatment based on the received electronic medical record.

[0236] Specific behavior:

[0237] The server transmits the electronic medical record to the medical institution using a secure communication channel (e.g., SSL / TLS).

[0238] The medical institution's terminal receives the electronic medical records and imports them into the system.

[0239] Medical staff prepare for treatment based on electronic medical records.

[0240] Input: Stored electronic medical record.

[0241] Output: Electronic medical records sent to the medical institution's terminal.

[0242] The above is a detailed description of the operation of each processing step of this system.

[0243] (Application example 1)

[0244] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0245] In today's world, accessing immediate health advice and medication recommendations in brick-and-mortar stores often requires the intervention of a medical professional. However, contacting a medical professional can be time-consuming, and the information needed to select the appropriate medication is often lacking. Furthermore, when additional medical information is required, the response can be delayed. Thus, providing prompt and appropriate health advice in brick-and-mortar stores presents a challenge.

[0246] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0247] In this invention, the server includes means for a user to input health information, means for analyzing the input information, means for generating an initial diagnosis based on the analysis results, means for automatically generating additional questions, means for making a final diagnosis based on the user's answers, means for generating an electronic medical record based on the final diagnosis results, means for saving the generated electronic medical record and the diagnosis results, means for guiding the user to an appropriate medical facility, means for transmitting the electronic medical record to the medical facility, means for presenting recommended medicines based on the final diagnosis results, and means for notifying a specialist if the user requests a detailed explanation. This enables users to receive prompt and appropriate health advice in a physical store.

[0248] A "user" is an individual who uses the system and inputs health information.

[0249] A "healthcare facility" is a place that provides healthcare services, such as a hospital, doctor's office, or clinic.

[0250] "Health-related information" refers to information related to the user's health condition, such as symptoms, medical history, and physical condition.

[0251] "Analysis" refers to processing health information and converting it into meaningful data.

[0252] The "initial diagnosis result" is a preliminary diagnosis result based on information input by the user.

[0253] "Additional questions" are questions automatically generated by the system to complement the initial diagnosis results.

[0254] The "final diagnosis" is a definitive diagnosis result based on the user's answers.

[0255] An "electronic medical record" is a record of a user's health information and diagnostic results stored in digital format.

[0256] "Preservation" refers to the safe and proper storage of generated data.

[0257] A "drug" is a substance intended to treat or prevent a disease or improve symptoms.

[0258] An "expert" is an individual who has knowledge of health information and pharmaceuticals and is qualified to provide detailed explanations to users.

[0259] A "server" is a computer that processes information from users and controls the entire system.

[0260] "Recommending" means presenting the best option.

[0261] "Notification" refers to an announcement that a particular action should be taken.

[0262] Overall system picture

[0263] The present invention is a system that allows users to input health information, analyzes the information, and provides diagnostic results and recommended medicines. How the system works and how it is implemented will be described below.

[0264] Hardware and software used

[0265] Hardware: Smartphones, tablets, servers

[0266] Software: Natural language processing technology (spacy), question answering models (transformers)

[0267] Processing flow

[0268] The system of this invention is mainly composed of three entities (user, terminal, and server). Each entity functions as follows:

[0269] 1. User information entry and submission

[0270] Users enter health information into the system via their smartphone or tablet. For example, they enter information like, "I have a sore throat and a slight fever." The entered information is sent from the device to the server.

[0271] 2. Information analysis by the server

[0272] The server uses natural language processing technology (spacy) to analyze the information sent by the user. Specifically, it extracts keywords such as "sore throat" and "fever" and generates an initial diagnosis based on these.

[0273] 3. Additional questions and diagnosis confirmation by the server

[0274] If the initial diagnosis is uncertain, the server uses a question-answering model (transformers) to automatically generate follow-up questions, such as "Do you have a cough or a headache?", and presents them to the user via the device. Once the user answers the follow-up questions, the information is reanalyzed to determine the final diagnosis.

[0275] 4. Generating and storing electronic medical records

[0276] Based on the final diagnosis, the server generates an electronic medical record, which contains the user's health information and diagnosis results and is securely stored.

[0277] 5. Presentation of recommended medications

[0278] Based on the final diagnosis, the server will recommend medicines to the user. For example, for a mild cold, it will display a list of medicines such as "Cold Medicine A" and "Cold Medicine B."

[0279] 6. Notice to Experts

[0280] If the user requests further explanation, the server will notify a specialist to provide further care to the user, allowing the user to receive prompt and appropriate health advice while in a physical store.

[0281] Specific examples

[0282] scenario:

[0283] The user types "I have a sore throat and a slight fever" into their smartphone.

[0284] The server generates a follow-up question: "Do you have a cough or a headache?", to which the user responds: "Yes, I have a slight cough."

[0285] The final diagnosis is a "mild cold," and "cold medicine A" or "cold medicine B" is recommended.

[0286] Prompt Sentence Examples

[0287] "When a user enters 'I have a sore throat and a slight fever,' please generate a program that displays the follow-up question 'Do you have a cough or a headache?'"

[0288] The above is a specific description of the "Mode for Carrying Out the Invention." As a result, the present invention provides users with prompt and appropriate health advice, thereby improving service at physical stores.

[0289] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0290] Step 1:

[0291] The user enters health information.

[0292] Input: Text information about the user's symptoms or health condition (e.g., "I have a sore throat and a slight fever").

[0293] Specific operation: The user uses a smartphone or tablet device to enter health information into the application and press the send button.

[0294] Output: The entered text information is sent to the server via the terminal.

[0295] Step 2:

[0296] The server analyzes the information it receives.

[0297] Input: Submitted text information about the user's health.

[0298] Data processing / calculation: The server uses natural language processing technology (spacy) to analyze the text and extract keywords such as "sore throat" and "fever."

[0299] Specific operation: The NLP model on the server analyzes the input text and extracts keywords related to the symptoms.

[0300] Output: A list of extracted keywords is generated.

[0301] Step 3:

[0302] The server generates an initial diagnosis.

[0303] Input: Extracted keyword list.

[0304] Data processing / calculation: The server applies a diagnostic algorithm and makes an initial diagnosis based on keywords.

[0305] How it works: An algorithm within the server evaluates the keyword list and generates an initial diagnosis, such as "suspected cold."

[0306] Output: An initial diagnostic result is generated and sent to the next step.

[0307] Step 4:

[0308] The server automatically generates additional questions.

[0309] Input: Initial diagnostic results.

[0310] Data transformation / computation: Question-answering models (transformers) are used to generate follow-up questions to complement the initial diagnostic results.

[0311] How it works: The AI ​​model in the server generates follow-up questions based on the initial diagnosis, such as "Do you have a cough or headache?"

[0312] Output: Generated follow-up questions are sent to the terminal.

[0313] Step 5:

[0314] The user answers additional questions.

[0315] Input: A follow-up question sent by the server.

[0316] Specific operation: The user checks the additional questions on a smartphone or tablet and enters an answer such as "Yes, I have a slight cough."

[0317] Output: The user's answer is sent to the server via the terminal.

[0318] Step 6:

[0319] The server performs the final diagnosis.

[0320] Input: The user's additional answer.

[0321] Data processing / calculation: The server reanalyzes the additional answers and determines the final diagnosis.

[0322] Specific operation: A diagnostic algorithm in the server comprehensively evaluates all the user's input data and generates a final diagnosis result such as "mild cold."

[0323] Output: The final diagnostic results are generated.

[0324] Step 7:

[0325] The server generates the electronic medical record.

[0326] Input: Final diagnosis and user health information.

[0327] Data processing / calculation: The server automatically generates the user's electronic medical record based on the final diagnosis results.

[0328] Specific operation: A program on the server combines diagnostic results and user information to create an electronic medical record.

[0329] Output: The generated electronic medical record is stored in a database.

[0330] Step 8:

[0331] The server presents recommended medications.

[0332] Input: Final diagnosis result.

[0333] Data processing / calculation: The server generates a list of recommended medicines based on the final diagnosis results.

[0334] Specific operation: The system within the server analyzes the diagnostic results and creates a list of relevant medications.

[0335] Output: A list of recommended medications is sent to the terminal.

[0336] Step 9:

[0337] Notify the expert.

[0338] Input: User's detailed description request.

[0339] Data processing / calculation: The server sends a notification to the expert.

[0340] Specific operation: The system in the server notifies the expert of the user's request for a detailed explanation.

[0341] Output: A notification is sent to the expert.

[0342] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0343] The present invention provides a system that allows users to input medical information, analyzes that information, and provides diagnostic results, and also incorporates an emotion engine that recognizes the user's emotional state and adjusts the diagnostic process based on that information, thereby providing more appropriate and personalized medical treatment. Below, we will explain how the system works and how it is specifically implemented.

[0344] Main processing of the program

[0345] 1. User symptom input

[0346] Users use devices such as smartphones or computers to input medical information into the AI ​​chatbot app.

[0347] For example, a user can input "I have a sore throat and a slight fever," and this information is sent to the server via the terminal.

[0348] 2. Recognizing emotional states

[0349] When a user inputs information through text or voice, the device uses an emotion engine to analyze the user's emotional state.

[0350] The emotion engine analyzes input text and voice and evaluates emotions such as whether the user is feeling stressed or anxious.

[0351] 3. Symptom analysis

[0352] The server analyzes the symptom information and emotional state data received from the device using natural language processing (NLP) technology.

[0353] The server analyzes keywords such as "sore throat" and "fever," as well as emotional information such as "anxiety" and "stress."

[0354] 4. Presenting the initial diagnosis and asking follow-up questions

[0355] The server generates an initial diagnosis based on the analysis results.

[0356] If the initial diagnosis is inconclusive, the server automatically generates additional questions.

[0357] Depending on the user's emotional state, for example, if the user is feeling stressed, the questions are softened or the explanations are made more detailed.

[0358] The terminal displays the additional questions sent from the server to the user.

[0359] 5. User Responses

[0360] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[0361] 6. Final diagnosis and medical record generation

[0362] The server re-analyzes the additional answers and provides a final diagnosis, for example, "a mild cold."

[0363] The server automatically generates an electronic medical record based on the user's medical condition and diagnosis results, and securely stores that information in a database.

[0364] 7. Information on specialized medical institutions

[0365] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[0366] Based on the analysis results of the emotion engine, users with high levels of stress or anxiety will receive individual support, such as being directed to medical institutions that can provide psychological counseling and mental care.

[0367] The server transmits information about appropriate medical institutions to the terminal and provides guidance to the user.

[0368] 8. AI medical record handover

[0369] The server securely transmits the user's electronic medical record to the medical institution where the user has completed an appointment.

[0370] The medical institution's terminal will then prepare for treatment based on the received electronic medical records, ensuring smooth treatment when the patient arrives.

[0371] Specific examples

[0372] scenario

[0373] Consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[0374] 1. User symptom input

[0375] The user (Taro) launches the app and enters, "I have a sore throat and a slight fever."

[0376] The terminal transmits this input information to the server.

[0377] 2. Recognizing emotional states

[0378] While the user is typing, the device uses an emotion engine to analyze Taro's emotional state and assesses that he is feeling "anxious."

[0379] 3. Symptom analysis

[0380] The server uses natural language processing to extract keywords such as "sore throat" and "fever" from the received data, and also performs an initial diagnosis by incorporating emotional information such as "anxiety."

[0381] 4. Presenting the initial diagnosis and asking follow-up questions

[0382] The server generates an initial diagnosis of "suspected cold."

[0383] To ease the user's anxiety, a follow-up question with detailed and gentle explanations is automatically generated: "Are you experiencing any other coughs or headaches?"

[0384] The terminal displays the question to Taro.

[0385] 5. User Responses

[0386] The user (Taro) responds, "Yes, I have a slight cough."

[0387] 6. Final diagnosis and medical record generation

[0388] The server reanalyzes the additional responses, makes a final diagnosis of "mild cold," and generates and securely stores an electronic medical record.

[0389] 7. Information on specialized medical institutions

[0390] The server will select an internal medicine clinic based on the electronic medical records and diagnosis results, and will also recommend a clinic that can provide mental care, taking into consideration Taro's concerns.

[0391] The server sends the medical institution information to the terminal and displays it to Taro.

[0392] Taro follows the instructions and makes a reservation.

[0393] 8. AI medical record handover

[0394] The server sends the electronic medical record to the clinic where the appointment is completed.

[0395] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[0396] In this way, incorporating an emotion engine makes it possible to provide a more personalized medical experience by responding to the user's emotional state in a more detailed manner.

[0397] The processing flow will be explained below.

[0398] Step 1:

[0399] Users launch the smartphone application and enter their symptoms by text or voice, for example, "I have a sore throat and a fever of 37.5 degrees."

[0400] Step 2:

[0401] The device receives the user's input information and simultaneously activates the emotion engine. The emotion engine analyzes the user's emotional state from the text and voice data entered. For example, it analyzes "anxiety" or "stress" from the words used and tone of voice when entering information.

[0402] Step 3:

[0403] The terminal transmits the analyzed emotion information and the symptom data of the user to the server.

[0404] Step 4:

[0405] The server analyzes the received symptom data and emotional information, passing the text data to a natural language processing (NLP) module to extract keywords such as "sore throat" and "fever," and then applies an initial diagnostic algorithm.

[0406] Step 5:

[0407] The server generates an initial diagnosis, for example, "suspected mild cold."

[0408] Step 6:

[0409] The server automatically generates additional questions taking into account emotional information. If the user is feeling anxious, the server softens the questions or provides detailed, easy-to-understand explanations. For example, it generates questions in the form of "Don't worry. Do you also have a cough or headache?"

[0410] Step 7:

[0411] The terminal displays the additional questions sent from the server to the user.

[0412] Step 8:

[0413] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[0414] Step 9:

[0415] The terminal transmits the user's response data to the server.

[0416] Step 10:

[0417] The server re-analyzes the additional responses and makes a final diagnosis, for example, a definitive diagnosis of "mild cold."

[0418] Step 11:

[0419] The server automatically generates an electronic medical record based on the user's symptoms, diagnosis results, and emotional information, and securely stores that information in a database.

[0420] Step 12:

[0421] The server selects medical institutions suitable for the user's area based on the generated electronic medical record and diagnosis results. Based on the emotional information, the server also provides additional information, such as clinics that can provide mental health care.

[0422] Step 13:

[0423] The server sends information about the selected medical institution to the terminal and provides the user with guidance, such as "The nearest internal medicine clinic is Hospital A. You can also receive mental health care there."

[0424] Step 14:

[0425] The user selects a medical institution based on the guidance and makes an appointment for a consultation.

[0426] Step 15:

[0427] The server securely transmits the user's electronic medical record and emotional information to the medical institution where the user has completed an appointment.

[0428] Step 16:

[0429] The medical institution's terminal receives the electronic medical record and emotional information sent from the server and prepares for treatment, ensuring smooth treatment when the patient arrives.

[0430] By going through these steps, users can receive prompt and appropriate medical services, and medical institutions can obtain detailed information in advance, resulting in more efficient medical treatment.In addition, the emotion engine enables flexible responses that take into account the user's psychological state.

[0431] Example 2

[0432] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0433] While conventional diagnostic systems can analyze a user's medical information and provide a diagnosis, they lack the ability to adjust the diagnostic process to take into account the user's emotional state, which can lead to users feeling stressed or anxious during the diagnosis process, resulting in a suboptimal medical experience.

[0434] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for a user to input medical information, a means for analyzing the input information, a means for generating an initial diagnosis based on the analysis results, a means for automatically generating additional questions, a means for recognizing the user's emotional state, a means for adjusting the diagnostic process based on the emotional state, a means for making a final diagnosis based on the user's answers, a means for generating an electronic medical record based on the final diagnosis result, a means for saving the generated electronic medical record and the diagnostic result, a means for guiding the user to an appropriate medical institution, and a means for transmitting the electronic medical record to the medical institution. This enables a detailed medical experience tailored to the user's emotional state, and more personalized medical care can be provided.

[0435] The term "user" refers to a person who uses this medical diagnostic system to input symptom information and the like.

[0436] "Medical information" refers to data entered by users regarding symptoms and health conditions.

[0437] "Emotional state" refers to the user's psychological reactions and feelings, including anxiety and stress about things.

[0438] "Means of analysis" refers to the techniques and algorithms used to process and analyze input data and extract meaningful information.

[0439] "Initial diagnosis result" refers to the first predicted diagnosis result obtained based on the input medical information.

[0440] "Means for automatically generating follow-up questions" refers to a technology or process that automatically generates follow-up questions to gather more detailed information based on the results of the initial diagnosis.

[0441] "Emotion engine" refers to the part of the system that includes the technology to recognize and analyze the user's emotional state from input data.

[0442] "Means for adjusting the diagnostic process" refers to technology for appropriately changing the diagnostic process and questions asked based on the user's emotional state.

[0443] "Final diagnosis" refers to a definitive diagnosis result obtained by analyzing all data, including the user's additional responses.

[0444] "Electronic Medical Record" means a medical record that stores a user's medical condition, diagnosis, and related information in digital form.

[0445] "Medical institution" refers to a facility such as a hospital or clinic that provides medical examinations and treatment.

[0446] "Natural language processing technology" refers to technology that allows computers to analyze, understand, and generate human language.

[0447] A "diagnostic algorithm" refers to a calculation procedure or method for making a diagnosis based on medical information.

[0448] A "generative AI model" refers to a model that uses artificial intelligence technology to generate new data and information.

[0449] The present invention provides a system that allows users to input medical information, analyzes that information, and provides diagnostic results. It also incorporates an emotion engine that recognizes the user's emotional state and adjusts the diagnostic process based on that information, thereby providing more appropriate and personalized medical treatment.

[0450] This system can be implemented using the following hardware and software. The hardware includes a smartphone or computer terminal for users to input medical information, and a server for analyzing data and generating diagnostic results. The software includes an AI chatbot app, an emotion engine, natural language processing (NLP) technology, and a diagnostic algorithm.

[0451] The specific system configuration and operation are as follows.

[0452] 1. User symptom input

[0453] Users use their smartphones or computers to input medical information into the AI ​​chatbot app, for example, "I have a sore throat and a slight fever."

[0454] 2. Recognizing emotional states

[0455] The device analyzes the user's input text (or voice) using an emotion engine, which uses NLP techniques and emotion analysis models to assess the user's emotional state, for example recognizing that the user is feeling anxious.

[0456] 3. Symptom analysis

[0457] The server uses NLP technology to analyze the symptom information and emotional state data received from the device. Specifically, it extracts keywords such as "sore throat" and "fever" and also analyzes the emotional information of "anxiety." This analysis uses a generative AI model and existing medical databases (e.g., Medline).

[0458] 4. Initial diagnosis and further questions

[0459] The server generates an initial diagnosis based on the analysis results. If the initial diagnosis is uncertain, the server automatically generates additional questions, such as "Do you have any other symptoms such as a cough or headache?" The questions are flexibly adjusted according to the patient's emotional state.

[0460] 5. Processing the User's Answers

[0461] The user answers the additional questions displayed on the terminal, for example, by typing "Yes, I have a slight cough."

[0462] 6. Final diagnosis and generation of electronic medical record

[0463] The server reanalyzes the user's additional answers and makes a final diagnosis, such as a "mild cold." It also generates and securely stores an electronic medical record based on the diagnosis.

[0464] 7. Medical Institution Information

[0465] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis. Taking into account the analysis results of the emotion engine, it also considers medical institutions that can provide psychological counseling and mental care. Information on appropriate medical institutions is sent to the terminal and directed to the user.

[0466] 8. AI medical record handover

[0467] The server securely transmits the electronic medical record to the medical institution where the user has made a reservation. The medical institution's terminal prepares for the medical treatment based on the received electronic medical record.

[0468] Specific examples

[0469] As an example, consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[0470] 1. User symptom input

[0471] Taro launches the app and types in, "I have a sore throat and a slight fever."

[0472] 2. Recognizing emotional states

[0473] The device analyzes the information Taro has entered and determines that he is feeling anxious.

[0474] 3. Symptom analysis

[0475] The server analyzes the received data using NLP technology and extracts keywords such as "sore throat," "fever," and "anxiety."

[0476] 4. Initial diagnosis and further questions

[0477] The initial diagnosis is "suspected cold," and a detailed follow-up question is automatically generated: "Do you have any other coughs or headaches?"

[0478] I'll present an additional question to Taro.

[0479] 5. Processing the User's Answers

[0480] Taro replies, "Yes, I have a slight cough."

[0481] 6. Final diagnosis and generation of electronic medical record

[0482] The server reanalyzes the additional responses and diagnoses the patient as having a mild cold. An electronic medical record is generated based on the diagnosis and stored securely.

[0483] 7. Medical Institution Information

[0484] Based on the electronic medical records and diagnosis results, the server will select an internal medicine clinic and also recommend a clinic that can provide mental care, taking into consideration Taro's anxiety.

[0485] Provide Taro with information about medical institutions.

[0486] 8. AI medical record handover

[0487] The server sends the medical record to the clinic where the reservation has been completed, and the medical institution prepares for treatment based on the received medical record.

[0488] As described above, the system of the present invention provides a detailed medical experience that is tailored to the user's emotional state, realizing personalized medical services.

[0489] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0490] Step 1: User symptom input

[0491] Users use their smartphones or computers to input medical information into the AI ​​chatbot app.

[0492] Example: "I have a sore throat and a slight fever."

[0493] Input: User's symptom information

[0494] Output: User input data stored on the device

[0495] Specific operation: Enter your symptoms into the app's input form and press the send button, and the data will be saved on your device.

[0496] Step 2: Recognizing your emotional state

[0497] The terminal analyzes the user's input text using an emotion engine.

[0498] The emotion engine uses NLP techniques and generative AI models to recognize emotions such as stress and anxiety.

[0499] Input: Text data entered by the user

[0500] Output: Emotional state (e.g., "anxiety")

[0501] Specific operation: The emotion engine analyzes the text and generates emotion tags. These tags are sent to the server.

[0502] Step 3: Symptom analysis

[0503] The server uses NLP technology to analyze the symptom information and emotional state data received from the device.

[0504] Keywords such as "sore throat" and "fever" are extracted, and analysis is performed including "anxiety." The generative AI model and medical databases (e.g., Medline) are referenced.

[0505] Input: Symptom information, emotional state data

[0506] Output: Initial diagnosis (e.g., "Suspected cold")

[0507] How it works: The NLP system extracts keywords, and the generative AI model references the medical database to generate an initial diagnosis.

[0508] Step 4: Initial diagnosis and further questions

[0509] The server generates an initial diagnosis based on the analysis results.

[0510] If the initial diagnosis is uncertain, a generative AI model is used to automatically generate follow-up questions, which are tailored based on the patient's emotional state.

[0511] Input: Analysis results (initial diagnosis)

[0512] Output: Initial diagnostic results and follow-up questions

[0513] Specific operation: The server performs an initial diagnosis, generates additional questions (e.g., "Do you have any other coughs or headaches?"), and sends the results to the device.

[0514] Step 5: Processing the user's answers

[0515] The user answers the additional questions displayed on the terminal.

[0516] For example, respond, "Yes, I have a slight cough."

[0517] Input: User's additional answer

[0518] Output: User response data saved on the device

[0519] Specific operation: When the user enters their answer into the app and presses the submit button, the data is saved on the device.

[0520] Step 6: Final diagnosis and electronic medical record generation

[0521] The server reanalyzes the user's additional answers and makes a final diagnosis.

[0522] A final diagnosis is determined using generative AI models and medical databases.

[0523] Input: Additional user answers, initial diagnosis results

[0524] Output: Final diagnosis (e.g., "Mild cold"), electronic medical record

[0525] Specific operation: The server analyzes the additional answers, makes a final diagnosis, and automatically generates and saves the results in the electronic medical record.

[0526] Step 7: Referral to a medical institution

[0527] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[0528] Taking into account the analysis results of the emotion engine, we will also consider medical institutions that can provide psychological counseling and mental care.

[0529] Input: Electronic medical records, final diagnosis results

[0530] Output: Appropriate medical institution information

[0531] Specific operation: The server selects a medical institution, sends information about the appropriate medical institution to the terminal, and guides the user.

[0532] Step 8: AI medical record handover

[0533] The server securely transmits the electronic medical record to the medical institution where the user has completed the reservation.

[0534] The medical institution's terminal prepares for medical treatment based on the received electronic medical record.

[0535] Input: Reservation information, electronic medical record

[0536] Output: Medical record data stored on the medical institution's terminal

[0537] Specific operation: The medical record is electronically sent from the server to the medical institution's terminal, and the medical institution prepares for treatment based on that information.

[0538] (Application example 2)

[0539] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0540] In autonomous vehicles, it is necessary for passengers and drivers to be able to quickly and accurately grasp their own health status and take necessary measures. In particular, for health-related input information, which is often influenced by emotional states, it is necessary to provide more appropriate and personalized medical assistance by recognizing emotions and adjusting the diagnostic process based on those emotions. However, with conventional systems, it has been difficult to integrate emotion recognition and health examinations and provide route guidance to the nearest medical institution in an emergency in cooperation with autonomous vehicles. These challenges must be resolved.

[0541] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0542] In this invention, the server includes means for recognizing the emotional state of the user, means for adjusting the diagnostic process based on the recognized emotional state, means for selecting and providing guidance to a medical institution according to the emotional state, and means for providing guidance on a route to the nearest medical institution in cooperation with the self-driving vehicle in an emergency. This enables a medical treatment process that takes the user's emotional state into consideration, and by cooperating with the self-driving vehicle, it is possible to respond quickly and appropriately in an emergency.

[0543] "User" refers to the passengers and drivers who use the system's health check function.

[0544] "Medical information" refers to all information entered by the user regarding health conditions, symptoms, and past medical history.

[0545] "Input means" refers to an interface that allows users to provide medical information to the system by voice or text. Examples include touch panels and voice recognition systems.

[0546] "Means of analysis" refers to technology that analyzes the medical information entered by the user and converts it into useful data. Natural language processing (NLP) technology is one example.

[0547] "Means for generating an initial diagnosis" refers to algorithms or techniques that generate an initial diagnosis based on the analyzed information.

[0548] "Means for automatically generating additional questions" refers to a technology that automatically creates questions necessary for further diagnosis when the initial diagnosis result is inconclusive.

[0549] The "means for making a final diagnosis" refers to a technology for determining the final results of a health check based on the user's answers to additional questions.

[0550] "Means for generating an electronic medical record" refers to a technology that creates a patient's medical record in electronic form based on the final diagnosis.

[0551] "Means for storing medical records and diagnostic results" refers to technology for securely storing the generated electronic medical records and diagnostic results in a database or cloud service.

[0552] "Means for guiding users to appropriate medical institutions" refers to a technology that suggests medical institutions that can provide appropriate medical services to users based on the final diagnosis results.

[0553] "Means for transmitting electronic medical records to medical institutions" refers to technology for securely transmitting the generated electronic medical records to the medical institution selected by the user.

[0554] "Means for recognizing emotional states" refers to technology that analyzes a user's emotional state using text, audio, and video input by the user.

[0555] "Means for adjusting the diagnostic process" refers to technology that tailors the content of the diagnosis or interview to suit the user based on the recognized emotional state.

[0556] "Means for selecting and providing guidance to medical institutions according to emotional state" refers to technology that selects a medical institution based on the results of analyzing the user's emotional state, taking into consideration appropriate mental care.

[0557] "Means of working with autonomous vehicles to provide route guidance to the nearest medical facility in an emergency" refers to technology that works with the navigation system of an autonomous vehicle to provide an emergency route to the most appropriate medical facility when a serious health problem is detected.

[0558] The present invention is a system that integrates health checkups and emotion recognition within an autonomous vehicle, enabling tailored responses to the user's health condition. In particular, it includes a means for recognizing the user's emotional state and adjusting the diagnostic process accordingly, and a means for linking the autonomous vehicle with the vehicle in an emergency to provide route guidance to the nearest medical facility.

[0559] Program Overview

[0560] The server, terminal, and user work together to perform the following processes.

[0561] User health information input

[0562] The user inputs medical information using the autonomous vehicle's touchscreen or voice input system. For example, the user might input, "I have chest pain and difficulty breathing." This input information is immediately transmitted to the server.

[0563] emotion recognition

[0564] When a user enters health information, the device uses a camera and microphone to analyze the user's facial expressions and voice to recognize their emotional state. An emotion recognition engine (e.g., Affectiva) is used to evaluate emotional states such as tension and fear.

[0565] Symptom analysis and early diagnosis

[0566] The server analyzes the input health information and emotion recognition data using natural language processing (NLP) technology. Specifically, it uses an NLP engine such as Google Cloud Natural Language to make an initial diagnosis based on the information such as "chest pain and difficulty breathing" and emotion data such as "tension" and "fear."

[0567] Generate follow-up questions

[0568] If the initial diagnosis is uncertain, the server generates follow-up questions, taking into account the perceived emotional state and generating softer, gentler questions, such as "Have you been feeling stressed lately?" or "Have you had similar symptoms in the past?"

[0569] User responses and final diagnosis

[0570] Once the user answers the additional questions, the server performs another analysis and makes a final diagnosis. The analysis is performed using a diagnostic algorithm (e.g., IBM Watson Health), and the final diagnosis is, for example, "mild cardiac abnormality."

[0571] Electronic medical record generation and storage

[0572] The server automatically generates and securely stores electronic medical records based on the final diagnosis results in a database or cloud storage.

[0573] Medical institution information

[0574] The server then guides the user to an appropriate medical institution based on the final diagnosis and emotional state. For example, if tension or fear is detected, it will recommend a medical institution that also provides mental care. Furthermore, if the situation is urgent, it will work with the autonomous vehicle's navigation system to automatically set a route to the nearest medical institution.

[0575] Specific examples

[0576] scenario

[0577] When a user enters "I have chest pain and difficulty breathing" in the car, the system uses an emotion recognition engine to detect emotions such as "tension" and "fear." As a result, the server performs an initial diagnosis, displays additional questions as necessary, and makes a final diagnosis. An electronic medical record is then generated and securely stored. In an emergency, the system works in conjunction with the autonomous vehicle's navigation system to provide route guidance to the nearest medical facility.

[0578] Prompt Sentence Examples

[0579] User: "My chest hurts and I'm having trouble breathing."

[0580] Emotional state: tension, fear

[0581] Initial diagnosis: Possible heart problem

[0582] Additional questions:

[0583] - "Have you been feeling stressed lately?"

[0584] - "Have you had similar symptoms in the past?"

[0585] Emergency Response:

[0586] - "This is likely an emergency, so we will escort you to the nearest medical facility. Please remain calm and wait."

[0587] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0588] Step 1:

[0589] User enters medical information

[0590] Input: The user inputs information about their health status using a touchscreen or voice recognition system inside the autonomous vehicle.

[0591] Action: The user types or speaks a symptom, such as "I have chest pain and difficulty breathing."

[0592] Output: The input information is stored as digital data on the terminal and sent to the server.

[0593] Step 2:

[0594] The device performs emotion recognition

[0595] Input: Health information, facial and voice data entered by the user.

[0596] How it works: It uses the camera and microphone to analyze the user's facial expressions and voice, and uses an emotion recognition engine (e.g., Affectiva) to assess their emotional state.

[0597] Output: The recognized emotional state (e.g., tension or fear) is sent as data from the device to the server.

[0598] Step 3:

[0599] The server analyzes health information and emotional data.

[0600] Input: User health and emotional state data.

[0601] How it works: The server uses natural language processing (NLP) technology (e.g., Google Cloud Natural Language) to analyze the health information entered and integrate it with emotional data.

[0602] Output: An initial diagnosis (e.g., possible cardiac issues) is generated as a result of the analysis.

[0603] Step 4:

[0604] The server generates a follow-up question

[0605] Input: Initial diagnosis and emotional state data.

[0606] How it works: Based on the initial diagnosis result, if the diagnosis is uncertain, the server generates soft questions depending on the emotional state.

[0607] Output: Follow-up questions (e.g., "Have you been feeling stressed lately?", "Have you had similar symptoms in the past?") are displayed to the chatbot.

[0608] Step 5:

[0609] The user answers additional questions

[0610] Input: The user's answer to the follow-up question.

[0611] What it does: The user types a response such as "Yes, it's stressful" or "No, this is the first time I've experienced something like this."

[0612] Output: The user's answers are stored digitally on the device and sent to the server.

[0613] Step 6:

[0614] The server makes the final diagnosis and generates the electronic medical record.

[0615] Input: Additional user answers and analytics data.

[0616] How it works: The server re-analyzes the data using a diagnostic algorithm (e.g., IBM Watson Health) to make a final diagnosis, automatically generates an electronic medical record based on the results, and securely stores the generated electronic medical record and the diagnosis results in a database.

[0617] Output: Final diagnosis (e.g., "Minor cardiac abnormality") and generated electronic medical record.

[0618] Step 7:

[0619] The server guides users to the appropriate medical institution.

[0620] Input: Final diagnosis and electronic medical record.

[0621] How it works: The server selects the most appropriate medical institution for the user based on the diagnosis results and emotional state, and works with the navigation system in the autonomous vehicle to provide directions to the appropriate medical institution.

[0622] Output: Medical facility information and route directions are displayed on the device.

[0623] Step 8:

[0624] Autonomous vehicles provide route guidance

[0625] Input: Route information to the selected medical facility.

[0626] How it works: The autonomous vehicle's navigation system creates an optimal route for the user and automatically guides the vehicle to a medical facility.

[0627] Output: The car will start driving automatically according to the optimal route and the user will reach the destination safely.

[0628] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0629] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0630] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0631] [Second embodiment]

[0632] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0633] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0634] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0635] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0636] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0637] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0638] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0639] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0640] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0641] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0642] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0643] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0644] The present invention is a system that allows a user to input medical information, analyzes the information, and provides a diagnosis. How the system operates and how it is specifically implemented will be described below.

[0645] Main processing of the program

[0646] 1. User symptom input

[0647] Users use devices such as smartphones or computers to input medical information into the AI ​​chatbot app.

[0648] For example, a user can input "I have a sore throat and a slight fever," and this information is sent to the server via the terminal.

[0649] 2. Symptom analysis

[0650] The server analyzes the symptom information received from the terminal using natural language processing (NLP) technology.

[0651] The server extracts keywords such as "sore throat" and "fever" and applies an initial diagnostic algorithm to identify potential diagnoses.

[0652] 3. Presenting the initial diagnosis and asking follow-up questions

[0653] The server generates an initial diagnosis based on the analysis results.

[0654] If the initial diagnosis is inconclusive, the server automatically generates additional questions and displays them to the user via the terminal.

[0655] The user answers the follow-up questions and sends, for example, "Yes, I have a slight cough."

[0656] 4. Final diagnosis and medical record generation

[0657] The server re-analyzes the additional answers and determines the final diagnosis, for example, a "mild cold."

[0658] The server automatically generates and securely stores electronic medical records containing the user's medical condition and diagnosis results.

[0659] 5. Information on specialized medical institutions

[0660] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[0661] The server transmits information about appropriate medical institutions to the terminal and provides guidance to the user.

[0662] The user can visit a medical institution based on the guidance.

[0663] 6. AI medical record handover

[0664] The server securely transmits the electronic medical record to the selected medical institution.

[0665] The medical institution's terminal prepares for medical treatment based on the received electronic medical record.

[0666] This allows the user to receive medical treatment smoothly.

[0667] Specific examples

[0668] scenario

[0669] Consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[0670] 1. User symptom input

[0671] The user (Taro) launches the app and enters, "I have a sore throat and a slight fever."

[0672] The terminal transmits this input information to the server.

[0673] 2. Symptom analysis

[0674] The server uses natural language processing to extract keywords such as "sore throat" and "fever" from the received information, and considers the possibility of a cold in the initial diagnosis.

[0675] 3. Presenting the initial diagnosis and asking follow-up questions

[0676] The server generates an initial diagnosis and determines that the patient "may have a cold."

[0677] To obtain additional information, the server generates a question, "Do you have a cough or headache?", and displays it on the device.

[0678] The user (Taro) responds, "Yes, I have a slight cough."

[0679] 4. Final diagnosis and medical record generation

[0680] The server reanalyzes the additional answers and determines the final diagnosis as "a mild cold."

[0681] The server generates an electronic medical record based on the diagnosis results and stores it securely.

[0682] 5. Information on specialized medical institutions

[0683] The server selects a nearby internal medicine clinic based on the electronic medical records and diagnosis results.

[0684] The server sends information about recommended medical institutions to the terminal and displays it to Taro.

[0685] The user (Taro) makes a reservation by following the instructions.

[0686] 6. AI medical record handover

[0687] The server sends the electronic medical record to the clinic where the appointment is completed.

[0688] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[0689] In this way, the present invention provides users with prompt and appropriate medical services and improves the efficiency of medical treatment at medical institutions.

[0690] The processing flow will be explained below.

[0691] Step 1:

[0692] Users launch the smartphone application and enter their symptoms by text or voice, for example, "I have a sore throat and a fever of 37.5 degrees."

[0693] Step 2:

[0694] The terminal receives the user's input information and transmits the text data to the server.

[0695] Step 3:

[0696] The server passes the received text data to a natural language processing (NLP) module to extract symptom keywords, such as "sore throat" and "fever."

[0697] Step 4:

[0698] The server applies an initial diagnosis algorithm based on the extracted keywords to generate an initial diagnosis result, for example, determining that there is a high possibility of a cold.

[0699] Step 5:

[0700] If the initial diagnosis result does not provide sufficient definitive information, the server automatically generates additional questions, such as "Do you have a cough or headache?"

[0701] Step 6:

[0702] The terminal displays the additional questions sent from the server to the user.

[0703] Step 7:

[0704] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[0705] Step 8:

[0706] The terminal transmits the user's additional responses to the server.

[0707] Step 9:

[0708] The server re-analyzes the additional responses and makes a final diagnosis, for example, a "mild cold."

[0709] Step 10:

[0710] The server automatically generates an electronic medical record based on the user's medical condition and diagnosis results, and securely stores that information in a database.

[0711] Step 11:

[0712] The server selects an appropriate medical institution in the user's area based on the final diagnosis and the generated electronic medical record.

[0713] Step 12:

[0714] The server sends information about the selected medical institution to the terminal and provides the user with guidance, such as "The nearest internal medicine clinic is Hospital A."

[0715] Step 13:

[0716] The user checks the information about the medical institution provided by the server and makes an appointment for a medical examination.

[0717] Step 14:

[0718] The server securely transmits the user's electronic medical record to the medical institution where the user has completed an appointment.

[0719] Step 15:

[0720] The medical institution's terminal receives the electronic medical records sent from the server and prepares for treatment, ensuring smooth treatment when the patient arrives.

[0721] In this way, the system of the present invention provides a seamless process from the user's symptom input to a final diagnosis and guidance to an appropriate medical institution, thereby streamlining medical access.

[0722] Example 1

[0723] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0724] There is a need for systems that allow users to input medical information, analyze that information appropriately, and provide a fast and accurate diagnosis, as well as automate the process of directing patients to appropriate medical institutions based on the diagnosis results and the safe transfer of electronic medical records. Furthermore, because conventional systems have difficulty selecting a medical institution appropriate for the user's area and improving the accuracy of diagnosis results, new technologies are needed to improve the quality of medical services.

[0725] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0726] In this invention, the server includes means for a user to input medical information, means for analyzing the input information, means for generating an initial diagnosis based on the analysis results, means for automatically generating additional questions, means for making a final diagnosis based on the user's answers, means for generating an electronic medical record based on the final diagnosis, means for saving the generated electronic medical record and the diagnosis results, means for directing the user to an appropriate medical institution, means for transmitting the electronic medical record to the medical institution, means for selecting a medical institution suitable for the user's area based on the electronic medical record and the diagnosis results, and means for securely transmitting the electronic medical record to the selected medical institution. This allows the user to receive a quick and accurate diagnosis, and enables directing to an appropriate medical institution and handing over the diagnosis results.

[0727] 1. "User" refers to a person who inputs medical information and receives diagnosis results and guidance on medical institutions.

[0728] 2. "Means for inputting information" means a device or interface used by a user to input medical information.

[0729] 3. "Means for analyzing information" refers to a system that uses data processing technology to analyze input information, extract keywords, and perform initial diagnosis.

[0730] 4. "Means for generating an initial diagnosis" means an algorithm or process that generates a preliminary diagnosis based on the analyzed information.

[0731] 5. "Means for automatically generating additional questions" refers to a system that automatically generates questions to obtain additional information necessary to improve the accuracy of initial diagnostic results.

[0732] 6. "Means for making a final diagnosis" means a system or process that reanalyzes the user's additional responses and determines a final diagnosis.

[0733] 7. "Means for generating electronic medical records" refers to a system that automatically creates electronic medical records that record diagnostic results and the user's medical condition.

[0734] 8. "Means for storing diagnostic results" means a system that stores the generated electronic medical records and diagnostic results in secure and reliable storage.

[0735] 9. "Means for guiding users to medical institutions" refers to a system that selects a medical institution suitable for the user based on the diagnosis results and provides that information to the user.

[0736] 10. "Means for transmitting electronic medical records" means the communications process and infrastructure for securely transmitting the generated electronic medical records to the selected healthcare provider.

[0737] 11. "Means for selecting a medical institution suitable for the area" refers to a system that selects the most suitable facility from local medical institutions based on the user's location information and diagnosis results.

[0738] 12. "Means for securely transmitting electronic medical records" means a system or protocol for transmitting electronic medical records to a medical institution using security such as encrypted communications.

[0739] This invention is a system in which a user inputs medical information, analyzes that information, and provides a diagnosis. The system is basically composed of a terminal, a server, and a medical institution's terminal. Each component of the system and its specific operation are described below.

[0740] Terminal

[0741] The terminal refers to a device such as a smartphone or PC that users use to input medical information. Specifically, they perform the following operations:

[0742] The user launches the application and enters information about their symptoms or illnesses.

[0743] For example, you might type, "I have a sore throat and a slight fever." This information is sent over the internet to a server.

[0744] server

[0745] The server is the main part that analyzes the information received from the user and generates the diagnosis results. The server uses the following hardware and software:

[0746] Hardware: Server equipment equipped with a high-performance CPU, sufficient memory, SSD storage, etc.

[0747] Software: TensorFlow and Spacy for natural language processing (NLP) techniques, MySQL for database management systems (DBMS), Scikit-learn and TensorFlow for diagnostic algorithms.

[0748] The operation of the server is as follows.

[0749] The information sent from the terminal is first stored in a database.

[0750] Next, an NLP model using TensorFlow and Spacy analyzes the input information and extracts keywords such as "sore throat" and "fever."

[0751] Based on the extracted keywords, an initial diagnosis algorithm (Scikit-learn or TensorFlow) is applied to generate initial diagnosis results.

[0752] If the initial diagnosis is uncertain, the server automatically generates additional questions and sends them to the terminal.

[0753] If the user answers additional questions, the information is sent back to the server for reanalysis.

[0754] Once the final diagnosis is confirmed, an electronic medical record is automatically generated and securely stored in an AWS S3 bucket or similar.

[0755] Based on the diagnosis results and electronic medical records, the system selects a medical institution suitable for the user's area. For example, it uses the Google Maps API to search for nearby medical institutions.

[0756] Medical institution terminals

[0757] The medical institution's terminal is a device for providing medical treatment based on the received electronic medical records.

[0758] Electronic medical records sent from the server are transmitted using encryption technology such as SSL / TLS.

[0759] The medical institution's terminal receives the electronic medical record, and medical staff prepare for treatment.

[0760] Specific examples

[0761] For example, if a user experiences cold-like symptoms, the system operates as follows.

[0762] 1. User symptom input

[0763] The user launches the app and types, "I have a sore throat and a slight fever."

[0764] The terminal sends this information to the server.

[0765] 2. Symptom analysis

[0766] The server uses NLP to extract keywords such as "sore throat" and "fever" from the received information, and considers the possibility of a cold in the initial diagnosis.

[0767] 3. Presenting the initial diagnosis and asking follow-up questions

[0768] The server generates an initial diagnosis of "suspected cold."

[0769] To get additional information, the server generates a question, "Do you have a cough or headache?", and displays it on the device.

[0770] The user responds, "Yes, I have a slight cough."

[0771] 4. Final diagnosis and medical record generation

[0772] The server reanalyzes the additional answers and determines the final diagnosis as "mild cold."

[0773] The server generates an electronic medical record based on the diagnosis results and stores it securely.

[0774] 5. Information on specialized medical institutions

[0775] Based on the electronic medical records and diagnosis results, the server selects a nearby internal medicine clinic and sends the information to the terminal.

[0776] The user makes a reservation by following the instructions.

[0777] 6. AI medical record handover

[0778] The server sends the electronic medical record to the clinic where the reservation is completed.

[0779] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[0780] Example prompts to input to the generative AI model

[0781] Example 1: "Describe a program that analyzes symptom information entered by a user and selects the most appropriate medical institution."

[0782] Example 2: "Given a patient's sore throat and mild fever, detail the process of using NLP to generate an initial diagnosis and follow-up questions, and then storing the final diagnosis in the electronic medical record."

[0783] This system provides users with accurate and prompt medical services, significantly improving the efficiency of medical treatment at medical institutions.

[0784] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0785] Step 1:

[0786] User symptom input

[0787] Users use their smartphones or computers to input symptom information into the AI ​​chatbot app, such as "sore throat" and "mild fever."

[0788] Specific behavior:

[0789] The user launches the app and enters "I have a sore throat and a slight fever" into the symptom entry form.

[0790] After entering the information, press the send button.

[0791] Input: Symptom information entered by the user.

[0792] Output: The device sends the input information to the server.

[0793] Step 2:

[0794] Symptom analysis

[0795] The server receives the symptom information sent from the device and analyzes it using natural language processing (NLP) technology. Specifically, it uses TensorFlow and Spacy to extract keywords such as "sore throat" and "fever" from the text data.

[0796] Specific behavior:

[0797] The server stores the received symptom data in a database.

[0798] An NLP model analyzes the data and extracts keywords.

[0799] Input: Symptom information received by the server.

[0800] Output: Extracted keywords "sore throat" and "fever".

[0801] Step 3:

[0802] Generate an initial diagnosis

[0803] Based on the extracted keywords, the server applies an initial diagnostic algorithm (using Scikit-learn or TensorFlow) to generate provisional diagnostic results.

[0804] Specific behavior:

[0805] The server runs an algorithm to provide an initial diagnosis corresponding to the symptoms.

[0806] The initial diagnosis result is "suspected cold."

[0807] Input: Extracted keywords.

[0808] Output: Initial diagnosis: "Suspected cold."

[0809] Step 4:

[0810] Generate and present follow-up questions

[0811] If the initial diagnosis is inconclusive, the server automatically generates additional questions and presents them to the user via the terminal, who then answers the questions.

[0812] Specific behavior:

[0813] The server generates follow-up questions based on the initial diagnostic results.

[0814] An additional question, "Do you have a cough or headache?", is generated and sent to the device.

[0815] The user receives the question and responds, "Yes, I have a slight cough."

[0816] Input: Initial diagnosis and follow-up questions.

[0817] Output: User answers "Yes, I have a slight cough."

[0818] Step 5:

[0819] Confirmation of final diagnosis and creation of medical records

[0820] The server reanalyzes the user's additional answers and determines the final diagnosis, which is a "mild cold." It also automatically generates and saves an electronic medical record based on the final diagnosis.

[0821] Specific behavior:

[0822] The server re-analyzes the additional answers and applies the final diagnostic algorithm.

[0823] The final diagnosis is confirmed as "mild cold."

[0824] Generate and securely store electronic medical records.

[0825] Input: The user's additional answer.

[0826] Output: Final diagnosis and electronic medical record.

[0827] Step 6:

[0828] Guide to specialized medical institutions

[0829] Based on the final diagnosis, the server selects a medical institution suitable for the user's area and sends that information to the terminal to guide the user.

[0830] Specific behavior:

[0831] The server uses Google Maps APIs and other tools to search for nearby medical institutions based on the user's location information.

[0832] Information on the appropriate medical institution is selected and sent to the terminal.

[0833] The user checks the information and makes a reservation.

[0834] Input: Electronic medical record and final diagnosis.

[0835] Output: Information on selected medical institutions.

[0836] Step 7:

[0837] AI medical record handover

[0838] The server securely transmits the electronic medical record to the selected medical institution, and the medical institution's terminal prepares for treatment based on the received electronic medical record.

[0839] Specific behavior:

[0840] The server transmits the electronic medical record to the medical institution using a secure communication channel (e.g., SSL / TLS).

[0841] The medical institution's terminal receives the electronic medical records and imports them into the system.

[0842] Medical staff prepare for treatment based on electronic medical records.

[0843] Input: Stored electronic medical record.

[0844] Output: Electronic medical records sent to the medical institution's terminal.

[0845] The above is a detailed description of the operation of each processing step of this system.

[0846] (Application example 1)

[0847] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0848] In today's world, accessing immediate health advice and medication recommendations in brick-and-mortar stores often requires the intervention of a medical professional. However, contacting a medical professional can be time-consuming, and the information needed to select the appropriate medication is often lacking. Furthermore, when additional medical information is required, the response can be delayed. Thus, providing prompt and appropriate health advice in brick-and-mortar stores presents a challenge.

[0849] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0850] In this invention, the server includes means for a user to input health information, means for analyzing the input information, means for generating an initial diagnosis based on the analysis results, means for automatically generating additional questions, means for making a final diagnosis based on the user's answers, means for generating an electronic medical record based on the final diagnosis results, means for saving the generated electronic medical record and the diagnosis results, means for guiding the user to an appropriate medical facility, means for transmitting the electronic medical record to the medical facility, means for presenting recommended medicines based on the final diagnosis results, and means for notifying a specialist if the user requests a detailed explanation. This enables users to receive prompt and appropriate health advice in a physical store.

[0851] A "user" is an individual who uses the system and inputs health information.

[0852] A "healthcare facility" is a place that provides healthcare services, such as a hospital, doctor's office, or clinic.

[0853] "Health-related information" refers to information related to the user's health condition, such as symptoms, medical history, and physical condition.

[0854] "Analysis" refers to processing health information and converting it into meaningful data.

[0855] The "initial diagnosis result" is a preliminary diagnosis result based on information input by the user.

[0856] "Additional questions" are questions automatically generated by the system to complement the initial diagnosis results.

[0857] The "final diagnosis" is a definitive diagnosis result based on the user's answers.

[0858] An "electronic medical record" is a record of a user's health information and diagnostic results stored in digital format.

[0859] "Preservation" refers to the safe and proper storage of generated data.

[0860] A "drug" is a substance intended to treat or prevent a disease or improve symptoms.

[0861] An "expert" is an individual who has knowledge of health information and pharmaceuticals and is qualified to provide detailed explanations to users.

[0862] A "server" is a computer that processes information from users and controls the entire system.

[0863] "Recommending" means presenting the best option.

[0864] "Notification" refers to an announcement that a particular action should be taken.

[0865] Overall system picture

[0866] The present invention is a system that allows users to input health information, analyzes the information, and provides diagnostic results and recommended medicines. How the system works and how it is implemented will be described below.

[0867] Hardware and software used

[0868] Hardware: Smartphones, tablets, servers

[0869] Software: Natural language processing technology (spacy), question answering models (transformers)

[0870] Processing flow

[0871] The system of this invention is mainly composed of three entities (user, terminal, and server). Each entity functions as follows:

[0872] 1. User information entry and submission

[0873] Users enter health information into the system via their smartphone or tablet. For example, they enter information like, "I have a sore throat and a slight fever." The entered information is sent from the device to the server.

[0874] 2. Information analysis by the server

[0875] The server uses natural language processing technology (spacy) to analyze the information sent by the user. Specifically, it extracts keywords such as "sore throat" and "fever" and generates an initial diagnosis based on these.

[0876] 3. Additional questions and diagnosis confirmation by the server

[0877] If the initial diagnosis is uncertain, the server uses a question-answering model (transformers) to automatically generate follow-up questions, such as "Do you have a cough or a headache?", and presents them to the user via the device. Once the user answers the follow-up questions, the information is reanalyzed to determine the final diagnosis.

[0878] 4. Generating and storing electronic medical records

[0879] Based on the final diagnosis, the server generates an electronic medical record, which contains the user's health information and diagnosis results and is securely stored.

[0880] 5. Presentation of recommended medications

[0881] Based on the final diagnosis, the server will recommend medicines to the user. For example, for a mild cold, it will display a list of medicines such as "Cold Medicine A" and "Cold Medicine B."

[0882] 6. Notice to Experts

[0883] If the user requests further explanation, the server will notify a specialist to provide further care to the user, allowing the user to receive prompt and appropriate health advice while in a physical store.

[0884] Specific examples

[0885] scenario:

[0886] The user types "I have a sore throat and a slight fever" into their smartphone.

[0887] The server generates a follow-up question: "Do you have a cough or a headache?", to which the user responds: "Yes, I have a slight cough."

[0888] The final diagnosis is a "mild cold," and "cold medicine A" or "cold medicine B" is recommended.

[0889] Prompt Sentence Examples

[0890] "When a user enters 'I have a sore throat and a slight fever,' please generate a program that displays the follow-up question 'Do you have a cough or a headache?'"

[0891] The above is a specific description of the "Mode for Carrying Out the Invention." As a result, the present invention provides users with prompt and appropriate health advice, thereby improving service at physical stores.

[0892] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0893] Step 1:

[0894] The user enters health information.

[0895] Input: Text information about the user's symptoms or health condition (e.g., "I have a sore throat and a slight fever").

[0896] Specific operation: The user uses a smartphone or tablet device to enter health information into the application and press the send button.

[0897] Output: The entered text information is sent to the server via the terminal.

[0898] Step 2:

[0899] The server analyzes the information it receives.

[0900] Input: Submitted text information about the user's health.

[0901] Data processing / calculation: The server uses natural language processing technology (spacy) to analyze the text and extract keywords such as "sore throat" and "fever."

[0902] Specific operation: The NLP model on the server analyzes the input text and extracts keywords related to the symptoms.

[0903] Output: A list of extracted keywords is generated.

[0904] Step 3:

[0905] The server generates an initial diagnosis.

[0906] Input: Extracted keyword list.

[0907] Data processing / calculation: The server applies a diagnostic algorithm and makes an initial diagnosis based on keywords.

[0908] How it works: An algorithm within the server evaluates the keyword list and generates an initial diagnosis, such as "suspected cold."

[0909] Output: An initial diagnostic result is generated and sent to the next step.

[0910] Step 4:

[0911] The server automatically generates additional questions.

[0912] Input: Initial diagnostic results.

[0913] Data transformation / computation: Question-answering models (transformers) are used to generate follow-up questions to complement the initial diagnostic results.

[0914] How it works: The AI ​​model in the server generates follow-up questions based on the initial diagnosis, such as "Do you have a cough or headache?"

[0915] Output: Generated follow-up questions are sent to the terminal.

[0916] Step 5:

[0917] The user answers additional questions.

[0918] Input: A follow-up question sent by the server.

[0919] Specific operation: The user checks the additional questions on a smartphone or tablet and enters an answer such as "Yes, I have a slight cough."

[0920] Output: The user's answer is sent to the server via the terminal.

[0921] Step 6:

[0922] The server performs the final diagnosis.

[0923] Input: The user's additional answer.

[0924] Data processing / calculation: The server reanalyzes the additional answers and determines the final diagnosis.

[0925] Specific operation: A diagnostic algorithm in the server comprehensively evaluates all the user's input data and generates a final diagnosis result such as "mild cold."

[0926] Output: The final diagnostic results are generated.

[0927] Step 7:

[0928] The server generates the electronic medical record.

[0929] Input: Final diagnosis and user health information.

[0930] Data processing / calculation: The server automatically generates the user's electronic medical record based on the final diagnosis results.

[0931] Specific operation: A program on the server combines diagnostic results and user information to create an electronic medical record.

[0932] Output: The generated electronic medical record is stored in a database.

[0933] Step 8:

[0934] The server presents recommended medications.

[0935] Input: Final diagnosis result.

[0936] Data processing / calculation: The server generates a list of recommended medicines based on the final diagnosis results.

[0937] Specific operation: The system within the server analyzes the diagnostic results and creates a list of relevant medications.

[0938] Output: A list of recommended medications is sent to the terminal.

[0939] Step 9:

[0940] Notify the expert.

[0941] Input: User's detailed description request.

[0942] Data processing / calculation: The server sends a notification to the expert.

[0943] Specific operation: The system in the server notifies the expert of the user's request for a detailed explanation.

[0944] Output: A notification is sent to the expert.

[0945] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0946] The present invention provides a system that allows users to input medical information, analyzes that information, and provides diagnostic results, and also incorporates an emotion engine that recognizes the user's emotional state and adjusts the diagnostic process based on that information, thereby providing more appropriate and personalized medical treatment. Below, we will explain how the system works and how it is specifically implemented.

[0947] Main processing of the program

[0948] 1. User symptom input

[0949] Users use devices such as smartphones or computers to input medical information into the AI ​​chatbot app.

[0950] For example, a user can input "I have a sore throat and a slight fever," and this information is sent to the server via the terminal.

[0951] 2. Recognizing emotional states

[0952] When a user inputs information through text or voice, the device uses an emotion engine to analyze the user's emotional state.

[0953] The emotion engine analyzes input text and voice and evaluates emotions such as whether the user is feeling stressed or anxious.

[0954] 3. Symptom analysis

[0955] The server analyzes the symptom information and emotional state data received from the device using natural language processing (NLP) technology.

[0956] The server analyzes keywords such as "sore throat" and "fever," as well as emotional information such as "anxiety" and "stress."

[0957] 4. Presenting the initial diagnosis and asking follow-up questions

[0958] The server generates an initial diagnosis based on the analysis results.

[0959] If the initial diagnosis is inconclusive, the server automatically generates additional questions.

[0960] Depending on the user's emotional state, for example, if the user is feeling stressed, the questions are softened or the explanations are made more detailed.

[0961] The terminal displays the additional questions sent from the server to the user.

[0962] 5. User Responses

[0963] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[0964] 6. Final diagnosis and medical record generation

[0965] The server re-analyzes the additional answers and provides a final diagnosis, for example, "a mild cold."

[0966] The server automatically generates an electronic medical record based on the user's medical condition and diagnosis results, and securely stores that information in a database.

[0967] 7. Information on specialized medical institutions

[0968] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[0969] Based on the analysis results of the emotion engine, users with high levels of stress or anxiety will receive individual support, such as being directed to medical institutions that can provide psychological counseling and mental care.

[0970] The server transmits information about appropriate medical institutions to the terminal and provides guidance to the user.

[0971] 8. AI medical record handover

[0972] The server securely transmits the user's electronic medical record to the medical institution where the user has completed an appointment.

[0973] The medical institution's terminal will then prepare for treatment based on the received electronic medical records, ensuring smooth treatment when the patient arrives.

[0974] Specific examples

[0975] scenario

[0976] Consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[0977] 1. User symptom input

[0978] The user (Taro) launches the app and enters, "I have a sore throat and a slight fever."

[0979] The terminal transmits this input information to the server.

[0980] 2. Recognizing emotional states

[0981] While the user is typing, the device uses an emotion engine to analyze Taro's emotional state and assesses that he is feeling "anxious."

[0982] 3. Symptom analysis

[0983] The server uses natural language processing to extract keywords such as "sore throat" and "fever" from the received data, and also performs an initial diagnosis by incorporating emotional information such as "anxiety."

[0984] 4. Presenting the initial diagnosis and asking follow-up questions

[0985] The server generates an initial diagnosis of "suspected cold."

[0986] To ease the user's anxiety, a follow-up question with detailed and gentle explanations is automatically generated: "Are you experiencing any other coughs or headaches?"

[0987] The terminal displays the question to Taro.

[0988] 5. User Responses

[0989] The user (Taro) responds, "Yes, I have a slight cough."

[0990] 6. Final diagnosis and medical record generation

[0991] The server reanalyzes the additional responses, makes a final diagnosis of "mild cold," and generates and securely stores an electronic medical record.

[0992] 7. Information on specialized medical institutions

[0993] The server will select an internal medicine clinic based on the electronic medical records and diagnosis results, and will also recommend a clinic that can provide mental care, taking into consideration Taro's concerns.

[0994] The server sends the medical institution information to the terminal and displays it to Taro.

[0995] Taro follows the instructions and makes a reservation.

[0996] 8. AI medical record handover

[0997] The server sends the electronic medical record to the clinic where the appointment is completed.

[0998] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[0999] In this way, incorporating an emotion engine makes it possible to provide a more personalized medical experience by responding to the user's emotional state in a more detailed manner.

[1000] The processing flow will be explained below.

[1001] Step 1:

[1002] Users launch the smartphone application and enter their symptoms by text or voice, for example, "I have a sore throat and a fever of 37.5 degrees."

[1003] Step 2:

[1004] The device receives the user's input information and simultaneously activates the emotion engine. The emotion engine analyzes the user's emotional state from the text and voice data entered. For example, it analyzes "anxiety" or "stress" from the words used and tone of voice when entering information.

[1005] Step 3:

[1006] The terminal transmits the analyzed emotion information and the symptom data of the user to the server.

[1007] Step 4:

[1008] The server analyzes the received symptom data and emotional information, passing the text data to a natural language processing (NLP) module to extract keywords such as "sore throat" and "fever," and then applies an initial diagnostic algorithm.

[1009] Step 5:

[1010] The server generates an initial diagnosis, for example, "suspected mild cold."

[1011] Step 6:

[1012] The server automatically generates additional questions taking into account emotional information. If the user is feeling anxious, the server softens the questions or provides detailed, easy-to-understand explanations. For example, it generates questions in the form of "Don't worry. Do you also have a cough or headache?"

[1013] Step 7:

[1014] The terminal displays the additional questions sent from the server to the user.

[1015] Step 8:

[1016] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[1017] Step 9:

[1018] The terminal transmits the user's response data to the server.

[1019] Step 10:

[1020] The server re-analyzes the additional responses and makes a final diagnosis, for example, a definitive diagnosis of "mild cold."

[1021] Step 11:

[1022] The server automatically generates an electronic medical record based on the user's symptoms, diagnosis results, and emotional information, and securely stores that information in a database.

[1023] Step 12:

[1024] The server selects medical institutions suitable for the user's area based on the generated electronic medical record and diagnosis results. Based on the emotional information, the server also provides additional information, such as clinics that can provide mental health care.

[1025] Step 13:

[1026] The server sends information about the selected medical institution to the terminal and provides the user with guidance, such as "The nearest internal medicine clinic is Hospital A. You can also receive mental health care there."

[1027] Step 14:

[1028] The user selects a medical institution based on the guidance and makes an appointment for a consultation.

[1029] Step 15:

[1030] The server securely transmits the user's electronic medical record and emotional information to the medical institution where the user has completed an appointment.

[1031] Step 16:

[1032] The medical institution's terminal receives the electronic medical record and emotional information sent from the server and prepares for treatment, ensuring smooth treatment when the patient arrives.

[1033] By going through these steps, users can receive prompt and appropriate medical services, and medical institutions can obtain detailed information in advance, resulting in more efficient medical treatment.In addition, the emotion engine enables flexible responses that take into account the user's psychological state.

[1034] Example 2

[1035] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1036] While conventional diagnostic systems can analyze a user's medical information and provide a diagnosis, they lack the ability to adjust the diagnostic process to take into account the user's emotional state, which can lead to users feeling stressed or anxious during the diagnosis process, resulting in a suboptimal medical experience.

[1037] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for a user to input medical information, a means for analyzing the input information, a means for generating an initial diagnosis based on the analysis results, a means for automatically generating additional questions, a means for recognizing the user's emotional state, a means for adjusting the diagnostic process based on the emotional state, a means for making a final diagnosis based on the user's answers, a means for generating an electronic medical record based on the final diagnosis result, a means for saving the generated electronic medical record and the diagnostic result, a means for guiding the user to an appropriate medical institution, and a means for transmitting the electronic medical record to the medical institution. This enables a detailed medical experience tailored to the user's emotional state, and more personalized medical care can be provided.

[1038] The term "user" refers to a person who uses this medical diagnostic system to input symptom information and the like.

[1039] "Medical information" refers to data entered by users regarding symptoms and health conditions.

[1040] "Emotional state" refers to the user's psychological reactions and feelings, including anxiety and stress about things.

[1041] "Means of analysis" refers to the techniques and algorithms used to process and analyze input data and extract meaningful information.

[1042] "Initial diagnosis result" refers to the first predicted diagnosis result obtained based on the input medical information.

[1043] "Means for automatically generating follow-up questions" refers to a technology or process that automatically generates follow-up questions to gather more detailed information based on the results of the initial diagnosis.

[1044] "Emotion engine" refers to the part of the system that includes the technology to recognize and analyze the user's emotional state from input data.

[1045] "Means for adjusting the diagnostic process" refers to technology for appropriately changing the diagnostic process and questions asked based on the user's emotional state.

[1046] "Final diagnosis" refers to a definitive diagnosis result obtained by analyzing all data, including the user's additional responses.

[1047] "Electronic Medical Record" means a medical record that stores a user's medical condition, diagnosis, and related information in digital form.

[1048] "Medical institution" refers to a facility such as a hospital or clinic that provides medical examinations and treatment.

[1049] "Natural language processing technology" refers to technology that allows computers to analyze, understand, and generate human language.

[1050] A "diagnostic algorithm" refers to a calculation procedure or method for making a diagnosis based on medical information.

[1051] A "generative AI model" refers to a model that uses artificial intelligence technology to generate new data and information.

[1052] The present invention provides a system that allows users to input medical information, analyzes that information, and provides diagnostic results. It also incorporates an emotion engine that recognizes the user's emotional state and adjusts the diagnostic process based on that information, thereby providing more appropriate and personalized medical treatment.

[1053] This system can be implemented using the following hardware and software. The hardware includes a smartphone or computer terminal for users to input medical information, and a server for analyzing data and generating diagnostic results. The software includes an AI chatbot app, an emotion engine, natural language processing (NLP) technology, and a diagnostic algorithm.

[1054] The specific system configuration and operation are as follows.

[1055] 1. User symptom input

[1056] Users use their smartphones or computers to input medical information into the AI ​​chatbot app, for example, "I have a sore throat and a slight fever."

[1057] 2. Recognizing emotional states

[1058] The device analyzes the user's input text (or voice) using an emotion engine, which uses NLP techniques and emotion analysis models to assess the user's emotional state, for example recognizing that the user is feeling anxious.

[1059] 3. Symptom analysis

[1060] The server uses NLP technology to analyze the symptom information and emotional state data received from the device. Specifically, it extracts keywords such as "sore throat" and "fever" and also analyzes the emotional information of "anxiety." This analysis uses a generative AI model and existing medical databases (e.g., Medline).

[1061] 4. Initial diagnosis and further questions

[1062] The server generates an initial diagnosis based on the analysis results. If the initial diagnosis is uncertain, the server automatically generates additional questions, such as "Do you have any other symptoms such as a cough or headache?" The questions are flexibly adjusted according to the patient's emotional state.

[1063] 5. Processing the User's Answers

[1064] The user answers the additional questions displayed on the terminal, for example, by typing "Yes, I have a slight cough."

[1065] 6. Final diagnosis and generation of electronic medical record

[1066] The server reanalyzes the user's additional answers and makes a final diagnosis, such as a "mild cold." It also generates and securely stores an electronic medical record based on the diagnosis.

[1067] 7. Medical Institution Information

[1068] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis. Taking into account the analysis results of the emotion engine, it also considers medical institutions that can provide psychological counseling and mental care. Information on appropriate medical institutions is sent to the terminal and directed to the user.

[1069] 8. AI medical record handover

[1070] The server securely transmits the electronic medical record to the medical institution where the user has made a reservation. The medical institution's terminal prepares for the medical treatment based on the received electronic medical record.

[1071] Specific examples

[1072] As an example, consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[1073] 1. User symptom input

[1074] Taro launches the app and types in, "I have a sore throat and a slight fever."

[1075] 2. Recognizing emotional states

[1076] The device analyzes the information Taro has entered and determines that he is feeling anxious.

[1077] 3. Symptom analysis

[1078] The server analyzes the received data using NLP technology and extracts keywords such as "sore throat," "fever," and "anxiety."

[1079] 4. Initial diagnosis and further questions

[1080] The initial diagnosis is "suspected cold," and a detailed follow-up question is automatically generated: "Do you have any other coughs or headaches?"

[1081] I'll present an additional question to Taro.

[1082] 5. Processing the User's Answers

[1083] Taro replies, "Yes, I have a slight cough."

[1084] 6. Final diagnosis and generation of electronic medical record

[1085] The server reanalyzes the additional responses and diagnoses the patient as having a mild cold. An electronic medical record is generated based on the diagnosis and stored securely.

[1086] 7. Medical Institution Information

[1087] Based on the electronic medical records and diagnosis results, the server will select an internal medicine clinic and also recommend a clinic that can provide mental care, taking into consideration Taro's anxiety.

[1088] Provide Taro with information about medical institutions.

[1089] 8. AI medical record handover

[1090] The server sends the medical record to the clinic where the reservation has been completed, and the medical institution prepares for treatment based on the received medical record.

[1091] As described above, the system of the present invention provides a detailed medical experience that is tailored to the user's emotional state, realizing personalized medical services.

[1092] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1093] Step 1: User symptom input

[1094] Users use their smartphones or computers to input medical information into the AI ​​chatbot app.

[1095] Example: "I have a sore throat and a slight fever."

[1096] Input: User's symptom information

[1097] Output: User input data stored on the device

[1098] Specific operation: Enter your symptoms into the app's input form and press the send button, and the data will be saved on your device.

[1099] Step 2: Recognizing your emotional state

[1100] The terminal analyzes the user's input text using an emotion engine.

[1101] The emotion engine uses NLP techniques and generative AI models to recognize emotions such as stress and anxiety.

[1102] Input: Text data entered by the user

[1103] Output: Emotional state (e.g., "anxiety")

[1104] Specific operation: The emotion engine analyzes the text and generates emotion tags. These tags are sent to the server.

[1105] Step 3: Symptom analysis

[1106] The server uses NLP technology to analyze the symptom information and emotional state data received from the device.

[1107] Keywords such as "sore throat" and "fever" are extracted, and analysis is performed including "anxiety." The generative AI model and medical databases (e.g., Medline) are referenced.

[1108] Input: Symptom information, emotional state data

[1109] Output: Initial diagnosis (e.g., "Suspected cold")

[1110] How it works: The NLP system extracts keywords, and the generative AI model references the medical database to generate an initial diagnosis.

[1111] Step 4: Initial diagnosis and further questions

[1112] The server generates an initial diagnosis based on the analysis results.

[1113] If the initial diagnosis is uncertain, a generative AI model is used to automatically generate follow-up questions, which are tailored based on the patient's emotional state.

[1114] Input: Analysis results (initial diagnosis)

[1115] Output: Initial diagnostic results and follow-up questions

[1116] Specific operation: The server performs an initial diagnosis, generates additional questions (e.g., "Do you have any other coughs or headaches?"), and sends the results to the device.

[1117] Step 5: Processing the user's answers

[1118] The user answers the additional questions displayed on the terminal.

[1119] For example, respond, "Yes, I have a slight cough."

[1120] Input: User's additional answer

[1121] Output: User response data saved on the device

[1122] Specific operation: When the user enters their answer into the app and presses the submit button, the data is saved on the device.

[1123] Step 6: Final diagnosis and electronic medical record generation

[1124] The server reanalyzes the user's additional answers and makes a final diagnosis.

[1125] A final diagnosis is determined using generative AI models and medical databases.

[1126] Input: Additional user answers, initial diagnosis results

[1127] Output: Final diagnosis (e.g., "Mild cold"), electronic medical record

[1128] Specific operation: The server analyzes the additional answers, makes a final diagnosis, and automatically generates and saves the results in the electronic medical record.

[1129] Step 7: Referral to a medical institution

[1130] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[1131] Taking into account the analysis results of the emotion engine, we will also consider medical institutions that can provide psychological counseling and mental care.

[1132] Input: Electronic medical records, final diagnosis results

[1133] Output: Appropriate medical institution information

[1134] Specific operation: The server selects a medical institution, sends information about the appropriate medical institution to the terminal, and guides the user.

[1135] Step 8: AI medical record handover

[1136] The server securely transmits the electronic medical record to the medical institution where the user has completed the reservation.

[1137] The medical institution's terminal prepares for medical treatment based on the received electronic medical record.

[1138] Input: Reservation information, electronic medical record

[1139] Output: Medical record data stored on the medical institution's terminal

[1140] Specific operation: The medical record is electronically sent from the server to the medical institution's terminal, and the medical institution prepares for treatment based on that information.

[1141] (Application example 2)

[1142] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1143] In autonomous vehicles, it is necessary for passengers and drivers to be able to quickly and accurately grasp their own health status and take necessary measures. In particular, for health-related input information, which is often influenced by emotional states, it is necessary to provide more appropriate and personalized medical assistance by recognizing emotions and adjusting the diagnostic process based on those emotions. However, with conventional systems, it has been difficult to integrate emotion recognition and health examinations and provide route guidance to the nearest medical institution in an emergency in cooperation with autonomous vehicles. These challenges must be resolved.

[1144] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1145] In this invention, the server includes means for recognizing the emotional state of the user, means for adjusting the diagnostic process based on the recognized emotional state, means for selecting and providing guidance to a medical institution according to the emotional state, and means for providing guidance on a route to the nearest medical institution in cooperation with the self-driving vehicle in an emergency. This enables a medical treatment process that takes the user's emotional state into consideration, and by cooperating with the self-driving vehicle, it is possible to respond quickly and appropriately in an emergency.

[1146] "User" refers to the passengers and drivers who use the system's health check function.

[1147] "Medical information" refers to all information entered by the user regarding health conditions, symptoms, and past medical history.

[1148] "Input means" refers to an interface that allows users to provide medical information to the system by voice or text. Examples include touch panels and voice recognition systems.

[1149] "Means of analysis" refers to technology that analyzes the medical information entered by the user and converts it into useful data. Natural language processing (NLP) technology is one example.

[1150] "Means for generating an initial diagnosis" refers to algorithms or techniques that generate an initial diagnosis based on the analyzed information.

[1151] "Means for automatically generating additional questions" refers to a technology that automatically creates questions necessary for further diagnosis when the initial diagnosis result is inconclusive.

[1152] The "means for making a final diagnosis" refers to a technology for determining the final results of a health check based on the user's answers to additional questions.

[1153] "Means for generating an electronic medical record" refers to a technology that creates a patient's medical record in electronic form based on the final diagnosis.

[1154] "Means for storing medical records and diagnostic results" refers to technology for securely storing the generated electronic medical records and diagnostic results in a database or cloud service.

[1155] "Means for guiding users to appropriate medical institutions" refers to a technology that suggests medical institutions that can provide appropriate medical services to users based on the final diagnosis results.

[1156] "Means for transmitting electronic medical records to medical institutions" refers to technology for securely transmitting the generated electronic medical records to the medical institution selected by the user.

[1157] "Means for recognizing emotional states" refers to technology that analyzes a user's emotional state using text, audio, and video input by the user.

[1158] "Means for adjusting the diagnostic process" refers to technology that tailors the content of the diagnosis or interview to suit the user based on the recognized emotional state.

[1159] "Means for selecting and providing guidance to medical institutions according to emotional state" refers to technology that selects a medical institution based on the results of analyzing the user's emotional state, taking into consideration appropriate mental care.

[1160] "Means of working with autonomous vehicles to provide route guidance to the nearest medical facility in an emergency" refers to technology that works with the navigation system of an autonomous vehicle to provide an emergency route to the most appropriate medical facility when a serious health problem is detected.

[1161] The present invention is a system that integrates health checkups and emotion recognition within an autonomous vehicle, enabling tailored responses to the user's health condition. In particular, it includes a means for recognizing the user's emotional state and adjusting the diagnostic process accordingly, and a means for linking the autonomous vehicle with the vehicle in an emergency to provide route guidance to the nearest medical facility.

[1162] Program Overview

[1163] The server, terminal, and user work together to perform the following processes.

[1164] User health information input

[1165] The user inputs medical information using the autonomous vehicle's touchscreen or voice input system. For example, the user might input, "I have chest pain and difficulty breathing." This input information is immediately transmitted to the server.

[1166] emotion recognition

[1167] When a user enters health information, the device uses a camera and microphone to analyze the user's facial expressions and voice to recognize their emotional state. An emotion recognition engine (e.g., Affectiva) is used to evaluate emotional states such as tension and fear.

[1168] Symptom analysis and early diagnosis

[1169] The server analyzes the input health information and emotion recognition data using natural language processing (NLP) technology. Specifically, it uses an NLP engine such as Google Cloud Natural Language to make an initial diagnosis based on the information such as "chest pain and difficulty breathing" and emotion data such as "tension" and "fear."

[1170] Generate follow-up questions

[1171] If the initial diagnosis is uncertain, the server generates follow-up questions, taking into account the perceived emotional state and generating softer, gentler questions, such as "Have you been feeling stressed lately?" or "Have you had similar symptoms in the past?"

[1172] User responses and final diagnosis

[1173] Once the user answers the additional questions, the server performs another analysis and makes a final diagnosis. The analysis is performed using a diagnostic algorithm (e.g., IBM Watson Health), and the final diagnosis is, for example, "mild cardiac abnormality."

[1174] Electronic medical record generation and storage

[1175] The server automatically generates and securely stores electronic medical records based on the final diagnosis results in a database or cloud storage.

[1176] Medical institution information

[1177] The server then guides the user to an appropriate medical institution based on the final diagnosis and emotional state. For example, if tension or fear is detected, it will recommend a medical institution that also provides mental care. Furthermore, if the situation is urgent, it will work with the autonomous vehicle's navigation system to automatically set a route to the nearest medical institution.

[1178] Specific examples

[1179] scenario

[1180] When a user enters "I have chest pain and difficulty breathing" in the car, the system uses an emotion recognition engine to detect emotions such as "tension" and "fear." As a result, the server performs an initial diagnosis, displays additional questions as necessary, and makes a final diagnosis. An electronic medical record is then generated and securely stored. In an emergency, the system works in conjunction with the autonomous vehicle's navigation system to provide route guidance to the nearest medical facility.

[1181] Prompt Sentence Examples

[1182] User: "My chest hurts and I'm having trouble breathing."

[1183] Emotional state: tension, fear

[1184] Initial diagnosis: Possible heart problem

[1185] Additional questions:

[1186] - "Have you been feeling stressed lately?"

[1187] - "Have you had similar symptoms in the past?"

[1188] Emergency Response:

[1189] - "This is likely an emergency, so we will escort you to the nearest medical facility. Please remain calm and wait."

[1190] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1191] Step 1:

[1192] User enters medical information

[1193] Input: The user inputs information about their health status using a touchscreen or voice recognition system inside the autonomous vehicle.

[1194] Action: The user types or speaks a symptom, such as "I have chest pain and difficulty breathing."

[1195] Output: The input information is stored as digital data on the terminal and sent to the server.

[1196] Step 2:

[1197] The device performs emotion recognition

[1198] Input: Health information, facial and voice data entered by the user.

[1199] How it works: It uses the camera and microphone to analyze the user's facial expressions and voice, and uses an emotion recognition engine (e.g., Affectiva) to assess their emotional state.

[1200] Output: The recognized emotional state (e.g., tension or fear) is sent as data from the device to the server.

[1201] Step 3:

[1202] The server analyzes health information and emotional data.

[1203] Input: User health and emotional state data.

[1204] How it works: The server uses natural language processing (NLP) technology (e.g., Google Cloud Natural Language) to analyze the health information entered and integrate it with emotional data.

[1205] Output: An initial diagnosis (e.g., possible cardiac issues) is generated as a result of the analysis.

[1206] Step 4:

[1207] The server generates a follow-up question

[1208] Input: Initial diagnosis and emotional state data.

[1209] How it works: Based on the initial diagnosis result, if the diagnosis is uncertain, the server generates soft questions depending on the emotional state.

[1210] Output: Follow-up questions (e.g., "Have you been feeling stressed lately?", "Have you had similar symptoms in the past?") are displayed to the chatbot.

[1211] Step 5:

[1212] The user answers additional questions

[1213] Input: The user's answer to the follow-up question.

[1214] What it does: The user types a response such as "Yes, it's stressful" or "No, this is the first time I've experienced something like this."

[1215] Output: The user's answers are stored digitally on the device and sent to the server.

[1216] Step 6:

[1217] The server makes the final diagnosis and generates the electronic medical record.

[1218] Input: Additional user answers and analytics data.

[1219] How it works: The server re-analyzes the data using a diagnostic algorithm (e.g., IBM Watson Health) to make a final diagnosis, automatically generates an electronic medical record based on the results, and securely stores the generated electronic medical record and the diagnosis results in a database.

[1220] Output: Final diagnosis (e.g., "Minor cardiac abnormality") and generated electronic medical record.

[1221] Step 7:

[1222] The server guides users to the appropriate medical institution.

[1223] Input: Final diagnosis and electronic medical record.

[1224] How it works: The server selects the most appropriate medical institution for the user based on the diagnosis results and emotional state, and works with the navigation system in the autonomous vehicle to provide directions to the appropriate medical institution.

[1225] Output: Medical facility information and route directions are displayed on the device.

[1226] Step 8:

[1227] Autonomous vehicles provide route guidance

[1228] Input: Route information to the selected medical facility.

[1229] How it works: The autonomous vehicle's navigation system creates an optimal route for the user and automatically guides the vehicle to a medical facility.

[1230] Output: The car will start driving automatically according to the optimal route and the user will reach the destination safely.

[1231] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1232] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1233] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1234] [Third embodiment]

[1235] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1236] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1237] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1238] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1239] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1240] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1241] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1242] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1243] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1244] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1245] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1246] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1247] The present invention is a system that allows a user to input medical information, analyzes the information, and provides a diagnosis. How the system operates and how it is specifically implemented will be described below.

[1248] Main processing of the program

[1249] 1. User symptom input

[1250] Users use devices such as smartphones or computers to input medical information into the AI ​​chatbot app.

[1251] For example, a user can input "I have a sore throat and a slight fever," and this information is sent to the server via the terminal.

[1252] 2. Symptom analysis

[1253] The server analyzes the symptom information received from the terminal using natural language processing (NLP) technology.

[1254] The server extracts keywords such as "sore throat" and "fever" and applies an initial diagnostic algorithm to identify potential diagnoses.

[1255] 3. Presenting the initial diagnosis and asking follow-up questions

[1256] The server generates an initial diagnosis based on the analysis results.

[1257] If the initial diagnosis is inconclusive, the server automatically generates additional questions and displays them to the user via the terminal.

[1258] The user answers the follow-up questions and sends, for example, "Yes, I have a slight cough."

[1259] 4. Final diagnosis and medical record generation

[1260] The server re-analyzes the additional answers and determines the final diagnosis, for example, a "mild cold."

[1261] The server automatically generates and securely stores electronic medical records containing the user's medical condition and diagnosis results.

[1262] 5. Information on specialized medical institutions

[1263] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[1264] The server transmits information about appropriate medical institutions to the terminal and provides guidance to the user.

[1265] The user can visit a medical institution based on the guidance.

[1266] 6. AI medical record handover

[1267] The server securely transmits the electronic medical record to the selected medical institution.

[1268] The medical institution's terminal prepares for medical treatment based on the received electronic medical record.

[1269] This allows the user to receive medical treatment smoothly.

[1270] Specific examples

[1271] scenario

[1272] Consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[1273] 1. User symptom input

[1274] The user (Taro) launches the app and enters, "I have a sore throat and a slight fever."

[1275] The terminal transmits this input information to the server.

[1276] 2. Symptom analysis

[1277] The server uses natural language processing to extract keywords such as "sore throat" and "fever" from the received information, and considers the possibility of a cold in the initial diagnosis.

[1278] 3. Presenting the initial diagnosis and asking follow-up questions

[1279] The server generates an initial diagnosis and determines that the patient "may have a cold."

[1280] To obtain additional information, the server generates a question, "Do you have a cough or headache?", and displays it on the device.

[1281] The user (Taro) responds, "Yes, I have a slight cough."

[1282] 4. Final diagnosis and medical record generation

[1283] The server reanalyzes the additional answers and determines the final diagnosis as "a mild cold."

[1284] The server generates an electronic medical record based on the diagnosis results and stores it securely.

[1285] 5. Information on specialized medical institutions

[1286] The server selects a nearby internal medicine clinic based on the electronic medical records and diagnosis results.

[1287] The server sends information about recommended medical institutions to the terminal and displays it to Taro.

[1288] The user (Taro) makes a reservation by following the instructions.

[1289] 6. AI medical record handover

[1290] The server sends the electronic medical record to the clinic where the appointment is completed.

[1291] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[1292] In this way, the present invention provides users with prompt and appropriate medical services and improves the efficiency of medical treatment at medical institutions.

[1293] The processing flow will be explained below.

[1294] Step 1:

[1295] Users launch the smartphone application and enter their symptoms by text or voice, for example, "I have a sore throat and a fever of 37.5 degrees."

[1296] Step 2:

[1297] The terminal receives the user's input information and transmits the text data to the server.

[1298] Step 3:

[1299] The server passes the received text data to a natural language processing (NLP) module to extract symptom keywords, such as "sore throat" and "fever."

[1300] Step 4:

[1301] The server applies an initial diagnosis algorithm based on the extracted keywords to generate an initial diagnosis result, for example, determining that there is a high possibility of a cold.

[1302] Step 5:

[1303] If the initial diagnosis result does not provide sufficient definitive information, the server automatically generates additional questions, such as "Do you have a cough or headache?"

[1304] Step 6:

[1305] The terminal displays the additional questions sent from the server to the user.

[1306] Step 7:

[1307] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[1308] Step 8:

[1309] The terminal transmits the user's additional responses to the server.

[1310] Step 9:

[1311] The server re-analyzes the additional responses and makes a final diagnosis, for example, a "mild cold."

[1312] Step 10:

[1313] The server automatically generates an electronic medical record based on the user's medical condition and diagnosis results, and securely stores that information in a database.

[1314] Step 11:

[1315] The server selects an appropriate medical institution in the user's area based on the final diagnosis and the generated electronic medical record.

[1316] Step 12:

[1317] The server sends information about the selected medical institution to the terminal and provides the user with guidance, such as "The nearest internal medicine clinic is Hospital A."

[1318] Step 13:

[1319] The user checks the information about the medical institution provided by the server and makes an appointment for a medical examination.

[1320] Step 14:

[1321] The server securely transmits the user's electronic medical record to the medical institution where the user has completed an appointment.

[1322] Step 15:

[1323] The medical institution's terminal receives the electronic medical records sent from the server and prepares for treatment, ensuring smooth treatment when the patient arrives.

[1324] In this way, the system of the present invention provides a seamless process from the user's symptom input to a final diagnosis and guidance to an appropriate medical institution, thereby streamlining medical access.

[1325] Example 1

[1326] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1327] There is a need for systems that allow users to input medical information, analyze that information appropriately, and provide a fast and accurate diagnosis, as well as automate the process of directing patients to appropriate medical institutions based on the diagnosis results and the safe transfer of electronic medical records. Furthermore, because conventional systems have difficulty selecting a medical institution appropriate for the user's area and improving the accuracy of diagnosis results, new technologies are needed to improve the quality of medical services.

[1328] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1329] In this invention, the server includes means for a user to input medical information, means for analyzing the input information, means for generating an initial diagnosis based on the analysis results, means for automatically generating additional questions, means for making a final diagnosis based on the user's answers, means for generating an electronic medical record based on the final diagnosis, means for saving the generated electronic medical record and the diagnosis results, means for directing the user to an appropriate medical institution, means for transmitting the electronic medical record to the medical institution, means for selecting a medical institution suitable for the user's area based on the electronic medical record and the diagnosis results, and means for securely transmitting the electronic medical record to the selected medical institution. This allows the user to receive a quick and accurate diagnosis, and enables directing to an appropriate medical institution and handing over the diagnosis results.

[1330] 1. "User" refers to a person who inputs medical information and receives diagnosis results and guidance on medical institutions.

[1331] 2. "Means for inputting information" means a device or interface used by a user to input medical information.

[1332] 3. "Means for analyzing information" refers to a system that uses data processing technology to analyze input information, extract keywords, and perform initial diagnosis.

[1333] 4. "Means for generating an initial diagnosis" means an algorithm or process that generates a preliminary diagnosis based on the analyzed information.

[1334] 5. "Means for automatically generating additional questions" refers to a system that automatically generates questions to obtain additional information necessary to improve the accuracy of initial diagnostic results.

[1335] 6. "Means for making a final diagnosis" means a system or process that reanalyzes the user's additional responses and determines a final diagnosis.

[1336] 7. "Means for generating electronic medical records" refers to a system that automatically creates electronic medical records that record diagnostic results and the user's medical condition.

[1337] 8. "Means for storing diagnostic results" means a system that stores the generated electronic medical records and diagnostic results in secure and reliable storage.

[1338] 9. "Means for guiding users to medical institutions" refers to a system that selects a medical institution suitable for the user based on the diagnosis results and provides that information to the user.

[1339] 10. "Means for transmitting electronic medical records" means the communications process and infrastructure for securely transmitting the generated electronic medical records to the selected healthcare provider.

[1340] 11. "Means for selecting a medical institution suitable for the area" refers to a system that selects the most suitable facility from local medical institutions based on the user's location information and diagnosis results.

[1341] 12. "Means for securely transmitting electronic medical records" means a system or protocol for transmitting electronic medical records to a medical institution using security such as encrypted communications.

[1342] This invention is a system in which a user inputs medical information, analyzes that information, and provides a diagnosis. The system is basically composed of a terminal, a server, and a medical institution's terminal. Each component of the system and its specific operation are described below.

[1343] Terminal

[1344] The terminal refers to a device such as a smartphone or PC that users use to input medical information. Specifically, they perform the following operations:

[1345] The user launches the application and enters information about their symptoms or illnesses.

[1346] For example, you might type, "I have a sore throat and a slight fever." This information is sent over the internet to a server.

[1347] server

[1348] The server is the main part that analyzes the information received from the user and generates the diagnosis results. The server uses the following hardware and software:

[1349] Hardware: Server equipment equipped with a high-performance CPU, sufficient memory, SSD storage, etc.

[1350] Software: TensorFlow and Spacy for natural language processing (NLP) techniques, MySQL for database management systems (DBMS), Scikit-learn and TensorFlow for diagnostic algorithms.

[1351] The operation of the server is as follows.

[1352] The information sent from the terminal is first stored in a database.

[1353] Next, an NLP model using TensorFlow and Spacy analyzes the input information and extracts keywords such as "sore throat" and "fever."

[1354] Based on the extracted keywords, an initial diagnosis algorithm (Scikit-learn or TensorFlow) is applied to generate initial diagnosis results.

[1355] If the initial diagnosis is uncertain, the server automatically generates additional questions and sends them to the terminal.

[1356] If the user answers additional questions, the information is sent back to the server for reanalysis.

[1357] Once the final diagnosis is confirmed, an electronic medical record is automatically generated and securely stored in an AWS S3 bucket or similar.

[1358] Based on the diagnosis results and electronic medical records, the system selects a medical institution suitable for the user's area. For example, it uses the Google Maps API to search for nearby medical institutions.

[1359] Medical institution terminals

[1360] The medical institution's terminal is a device for providing medical treatment based on the received electronic medical records.

[1361] Electronic medical records sent from the server are transmitted using encryption technology such as SSL / TLS.

[1362] The medical institution's terminal receives the electronic medical record, and medical staff prepare for treatment.

[1363] Specific examples

[1364] For example, if a user experiences cold-like symptoms, the system operates as follows.

[1365] 1. User symptom input

[1366] The user launches the app and types, "I have a sore throat and a slight fever."

[1367] The terminal sends this information to the server.

[1368] 2. Symptom analysis

[1369] The server uses NLP to extract keywords such as "sore throat" and "fever" from the received information, and considers the possibility of a cold in the initial diagnosis.

[1370] 3. Presenting the initial diagnosis and asking follow-up questions

[1371] The server generates an initial diagnosis of "suspected cold."

[1372] To get additional information, the server generates a question, "Do you have a cough or headache?", and displays it on the device.

[1373] The user responds, "Yes, I have a slight cough."

[1374] 4. Final diagnosis and medical record generation

[1375] The server reanalyzes the additional answers and determines the final diagnosis as "mild cold."

[1376] The server generates an electronic medical record based on the diagnosis results and stores it securely.

[1377] 5. Information on specialized medical institutions

[1378] Based on the electronic medical records and diagnosis results, the server selects a nearby internal medicine clinic and sends the information to the terminal.

[1379] The user makes a reservation by following the instructions.

[1380] 6. AI medical record handover

[1381] The server sends the electronic medical record to the clinic where the reservation is completed.

[1382] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[1383] Example prompts to input to the generative AI model

[1384] Example 1: "Describe a program that analyzes symptom information entered by a user and selects the most appropriate medical institution."

[1385] Example 2: "Given a patient's sore throat and mild fever, detail the process of using NLP to generate an initial diagnosis and follow-up questions, and then storing the final diagnosis in the electronic medical record."

[1386] This system provides users with accurate and prompt medical services, significantly improving the efficiency of medical treatment at medical institutions.

[1387] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1388] Step 1:

[1389] User symptom input

[1390] Users use their smartphones or computers to input symptom information into the AI ​​chatbot app, such as "sore throat" and "mild fever."

[1391] Specific behavior:

[1392] The user launches the app and enters "I have a sore throat and a slight fever" into the symptom entry form.

[1393] After entering the information, press the send button.

[1394] Input: Symptom information entered by the user.

[1395] Output: The device sends the input information to the server.

[1396] Step 2:

[1397] Symptom analysis

[1398] The server receives the symptom information sent from the device and analyzes it using natural language processing (NLP) technology. Specifically, it uses TensorFlow and Spacy to extract keywords such as "sore throat" and "fever" from the text data.

[1399] Specific behavior:

[1400] The server stores the received symptom data in a database.

[1401] An NLP model analyzes the data and extracts keywords.

[1402] Input: Symptom information received by the server.

[1403] Output: Extracted keywords "sore throat" and "fever".

[1404] Step 3:

[1405] Generate an initial diagnosis

[1406] Based on the extracted keywords, the server applies an initial diagnostic algorithm (using Scikit-learn or TensorFlow) to generate provisional diagnostic results.

[1407] Specific behavior:

[1408] The server runs an algorithm to provide an initial diagnosis corresponding to the symptoms.

[1409] The initial diagnosis result is "suspected cold."

[1410] Input: Extracted keywords.

[1411] Output: Initial diagnosis: "Suspected cold."

[1412] Step 4:

[1413] Generate and present follow-up questions

[1414] If the initial diagnosis is inconclusive, the server automatically generates additional questions and presents them to the user via the terminal, who then answers the questions.

[1415] Specific behavior:

[1416] The server generates follow-up questions based on the initial diagnostic results.

[1417] An additional question, "Do you have a cough or headache?", is generated and sent to the device.

[1418] The user receives the question and responds, "Yes, I have a slight cough."

[1419] Input: Initial diagnosis and follow-up questions.

[1420] Output: User answers "Yes, I have a slight cough."

[1421] Step 5:

[1422] Confirmation of final diagnosis and creation of medical records

[1423] The server reanalyzes the user's additional answers and determines the final diagnosis, which is a "mild cold." It also automatically generates and saves an electronic medical record based on the final diagnosis.

[1424] Specific behavior:

[1425] The server re-analyzes the additional answers and applies the final diagnostic algorithm.

[1426] The final diagnosis is confirmed as "mild cold."

[1427] Generate and securely store electronic medical records.

[1428] Input: The user's additional answer.

[1429] Output: Final diagnosis and electronic medical record.

[1430] Step 6:

[1431] Guide to specialized medical institutions

[1432] Based on the final diagnosis, the server selects a medical institution suitable for the user's area and sends that information to the terminal to guide the user.

[1433] Specific behavior:

[1434] The server uses Google Maps APIs and other tools to search for nearby medical institutions based on the user's location information.

[1435] Information on the appropriate medical institution is selected and sent to the terminal.

[1436] The user checks the information and makes a reservation.

[1437] Input: Electronic medical record and final diagnosis.

[1438] Output: Information on selected medical institutions.

[1439] Step 7:

[1440] AI medical record handover

[1441] The server securely transmits the electronic medical record to the selected medical institution, and the medical institution's terminal prepares for treatment based on the received electronic medical record.

[1442] Specific behavior:

[1443] The server transmits the electronic medical record to the medical institution using a secure communication channel (e.g., SSL / TLS).

[1444] The medical institution's terminal receives the electronic medical records and imports them into the system.

[1445] Medical staff prepare for treatment based on electronic medical records.

[1446] Input: Stored electronic medical record.

[1447] Output: Electronic medical records sent to the medical institution's terminal.

[1448] The above is a detailed description of the operation of each processing step of this system.

[1449] (Application example 1)

[1450] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1451] In today's world, accessing immediate health advice and medication recommendations in brick-and-mortar stores often requires the intervention of a medical professional. However, contacting a medical professional can be time-consuming, and the information needed to select the appropriate medication is often lacking. Furthermore, when additional medical information is required, the response can be delayed. Thus, providing prompt and appropriate health advice in brick-and-mortar stores presents a challenge.

[1452] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1453] In this invention, the server includes means for a user to input health information, means for analyzing the input information, means for generating an initial diagnosis based on the analysis results, means for automatically generating additional questions, means for making a final diagnosis based on the user's answers, means for generating an electronic medical record based on the final diagnosis results, means for saving the generated electronic medical record and the diagnosis results, means for guiding the user to an appropriate medical facility, means for transmitting the electronic medical record to the medical facility, means for presenting recommended medicines based on the final diagnosis results, and means for notifying a specialist if the user requests a detailed explanation. This enables users to receive prompt and appropriate health advice in a physical store.

[1454] A "user" is an individual who uses the system and inputs health information.

[1455] A "healthcare facility" is a place that provides healthcare services, such as a hospital, doctor's office, or clinic.

[1456] "Health-related information" refers to information related to the user's health condition, such as symptoms, medical history, and physical condition.

[1457] "Analysis" refers to processing health information and converting it into meaningful data.

[1458] The "initial diagnosis result" is a preliminary diagnosis result based on information input by the user.

[1459] "Additional questions" are questions automatically generated by the system to complement the initial diagnosis results.

[1460] The "final diagnosis" is a definitive diagnosis result based on the user's answers.

[1461] An "electronic medical record" is a record of a user's health information and diagnostic results stored in digital format.

[1462] "Preservation" refers to the safe and proper storage of generated data.

[1463] A "drug" is a substance intended to treat or prevent a disease or improve symptoms.

[1464] An "expert" is an individual who has knowledge of health information and pharmaceuticals and is qualified to provide detailed explanations to users.

[1465] A "server" is a computer that processes information from users and controls the entire system.

[1466] "Recommending" means presenting the best option.

[1467] "Notification" refers to an announcement that a particular action should be taken.

[1468] Overall system picture

[1469] The present invention is a system that allows users to input health information, analyzes the information, and provides diagnostic results and recommended medicines. How the system works and how it is implemented will be described below.

[1470] Hardware and software used

[1471] Hardware: Smartphones, tablets, servers

[1472] Software: Natural language processing technology (spacy), question answering models (transformers)

[1473] Processing flow

[1474] The system of this invention is mainly composed of three entities (user, terminal, and server). Each entity functions as follows:

[1475] 1. User information entry and submission

[1476] Users enter health information into the system via their smartphone or tablet. For example, they enter information like, "I have a sore throat and a slight fever." The entered information is sent from the device to the server.

[1477] 2. Information analysis by the server

[1478] The server uses natural language processing technology (spacy) to analyze the information sent by the user. Specifically, it extracts keywords such as "sore throat" and "fever" and generates an initial diagnosis based on these.

[1479] 3. Additional questions and diagnosis confirmation by the server

[1480] If the initial diagnosis is uncertain, the server uses a question-answering model (transformers) to automatically generate follow-up questions, such as "Do you have a cough or a headache?", and presents them to the user via the device. Once the user answers the follow-up questions, the information is reanalyzed to determine the final diagnosis.

[1481] 4. Generating and storing electronic medical records

[1482] Based on the final diagnosis, the server generates an electronic medical record, which contains the user's health information and diagnosis results and is securely stored.

[1483] 5. Presentation of recommended medications

[1484] Based on the final diagnosis, the server will recommend medicines to the user. For example, for a mild cold, it will display a list of medicines such as "Cold Medicine A" and "Cold Medicine B."

[1485] 6. Notice to Experts

[1486] If the user requests further explanation, the server will notify a specialist to provide further care to the user, allowing the user to receive prompt and appropriate health advice while in a physical store.

[1487] Specific examples

[1488] scenario:

[1489] The user types "I have a sore throat and a slight fever" into their smartphone.

[1490] The server generates a follow-up question: "Do you have a cough or a headache?", to which the user responds: "Yes, I have a slight cough."

[1491] The final diagnosis is a "mild cold," and "cold medicine A" or "cold medicine B" is recommended.

[1492] Prompt Sentence Examples

[1493] "When a user enters 'I have a sore throat and a slight fever,' please generate a program that displays the follow-up question 'Do you have a cough or a headache?'"

[1494] The above is a specific description of the "Mode for Carrying Out the Invention." As a result, the present invention provides users with prompt and appropriate health advice, thereby improving service at physical stores.

[1495] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1496] Step 1:

[1497] The user enters health information.

[1498] Input: Text information about the user's symptoms or health condition (e.g., "I have a sore throat and a slight fever").

[1499] Specific operation: The user uses a smartphone or tablet device to enter health information into the application and press the send button.

[1500] Output: The entered text information is sent to the server via the terminal.

[1501] Step 2:

[1502] The server analyzes the information it receives.

[1503] Input: Submitted text information about the user's health.

[1504] Data processing / calculation: The server uses natural language processing technology (spacy) to analyze the text and extract keywords such as "sore throat" and "fever."

[1505] Specific operation: The NLP model on the server analyzes the input text and extracts keywords related to the symptoms.

[1506] Output: A list of extracted keywords is generated.

[1507] Step 3:

[1508] The server generates an initial diagnosis.

[1509] Input: Extracted keyword list.

[1510] Data processing / calculation: The server applies a diagnostic algorithm and makes an initial diagnosis based on keywords.

[1511] How it works: An algorithm within the server evaluates the keyword list and generates an initial diagnosis, such as "suspected cold."

[1512] Output: An initial diagnostic result is generated and sent to the next step.

[1513] Step 4:

[1514] The server automatically generates additional questions.

[1515] Input: Initial diagnostic results.

[1516] Data transformation / computation: Question-answering models (transformers) are used to generate follow-up questions to complement the initial diagnostic results.

[1517] How it works: The AI ​​model in the server generates follow-up questions based on the initial diagnosis, such as "Do you have a cough or headache?"

[1518] Output: Generated follow-up questions are sent to the terminal.

[1519] Step 5:

[1520] The user answers additional questions.

[1521] Input: A follow-up question sent by the server.

[1522] Specific operation: The user checks the additional questions on a smartphone or tablet and enters an answer such as "Yes, I have a slight cough."

[1523] Output: The user's answer is sent to the server via the terminal.

[1524] Step 6:

[1525] The server performs the final diagnosis.

[1526] Input: The user's additional answer.

[1527] Data processing / calculation: The server reanalyzes the additional answers and determines the final diagnosis.

[1528] Specific operation: A diagnostic algorithm in the server comprehensively evaluates all the user's input data and generates a final diagnosis result such as "mild cold."

[1529] Output: The final diagnostic results are generated.

[1530] Step 7:

[1531] The server generates the electronic medical record.

[1532] Input: Final diagnosis and user health information.

[1533] Data processing / calculation: The server automatically generates the user's electronic medical record based on the final diagnosis results.

[1534] Specific operation: A program on the server combines diagnostic results and user information to create an electronic medical record.

[1535] Output: The generated electronic medical record is stored in a database.

[1536] Step 8:

[1537] The server presents recommended medications.

[1538] Input: Final diagnosis result.

[1539] Data processing / calculation: The server generates a list of recommended medicines based on the final diagnosis results.

[1540] Specific operation: The system within the server analyzes the diagnostic results and creates a list of relevant medications.

[1541] Output: A list of recommended medications is sent to the terminal.

[1542] Step 9:

[1543] Notify the expert.

[1544] Input: User's detailed description request.

[1545] Data processing / calculation: The server sends a notification to the expert.

[1546] Specific operation: The system in the server notifies the expert of the user's request for a detailed explanation.

[1547] Output: A notification is sent to the expert.

[1548] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1549] The present invention provides a system that allows users to input medical information, analyzes that information, and provides diagnostic results, and also incorporates an emotion engine that recognizes the user's emotional state and adjusts the diagnostic process based on that information, thereby providing more appropriate and personalized medical treatment. Below, we will explain how the system works and how it is specifically implemented.

[1550] Main processing of the program

[1551] 1. User symptom input

[1552] Users use devices such as smartphones or computers to input medical information into the AI ​​chatbot app.

[1553] For example, a user can input "I have a sore throat and a slight fever," and this information is sent to the server via the terminal.

[1554] 2. Recognizing emotional states

[1555] When a user inputs information through text or voice, the device uses an emotion engine to analyze the user's emotional state.

[1556] The emotion engine analyzes input text and voice and evaluates emotions such as whether the user is feeling stressed or anxious.

[1557] 3. Symptom analysis

[1558] The server analyzes the symptom information and emotional state data received from the device using natural language processing (NLP) technology.

[1559] The server analyzes keywords such as "sore throat" and "fever," as well as emotional information such as "anxiety" and "stress."

[1560] 4. Presenting the initial diagnosis and asking follow-up questions

[1561] The server generates an initial diagnosis based on the analysis results.

[1562] If the initial diagnosis is inconclusive, the server automatically generates additional questions.

[1563] Depending on the user's emotional state, for example, if the user is feeling stressed, the questions are softened or the explanations are made more detailed.

[1564] The terminal displays the additional questions sent from the server to the user.

[1565] 5. User Responses

[1566] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[1567] 6. Final diagnosis and medical record generation

[1568] The server re-analyzes the additional answers and provides a final diagnosis, for example, "a mild cold."

[1569] The server automatically generates an electronic medical record based on the user's medical condition and diagnosis results, and securely stores that information in a database.

[1570] 7. Information on specialized medical institutions

[1571] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[1572] Based on the analysis results of the emotion engine, users with high levels of stress or anxiety will receive individual support, such as being directed to medical institutions that can provide psychological counseling and mental care.

[1573] The server transmits information about appropriate medical institutions to the terminal and provides guidance to the user.

[1574] 8. AI medical record handover

[1575] The server securely transmits the user's electronic medical record to the medical institution where the user has completed an appointment.

[1576] The medical institution's terminal will then prepare for treatment based on the received electronic medical records, ensuring smooth treatment when the patient arrives.

[1577] Specific examples

[1578] scenario

[1579] Consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[1580] 1. User symptom input

[1581] The user (Taro) launches the app and enters, "I have a sore throat and a slight fever."

[1582] The terminal transmits this input information to the server.

[1583] 2. Recognizing emotional states

[1584] While the user is typing, the device uses an emotion engine to analyze Taro's emotional state and assesses that he is feeling "anxious."

[1585] 3. Symptom analysis

[1586] The server uses natural language processing to extract keywords such as "sore throat" and "fever" from the received data, and also performs an initial diagnosis by incorporating emotional information such as "anxiety."

[1587] 4. Presenting the initial diagnosis and asking follow-up questions

[1588] The server generates an initial diagnosis of "suspected cold."

[1589] To ease the user's anxiety, a follow-up question with detailed and gentle explanations is automatically generated: "Are you experiencing any other coughs or headaches?"

[1590] The terminal displays the question to Taro.

[1591] 5. User Responses

[1592] The user (Taro) responds, "Yes, I have a slight cough."

[1593] 6. Final diagnosis and medical record generation

[1594] The server reanalyzes the additional responses, makes a final diagnosis of "mild cold," and generates and securely stores an electronic medical record.

[1595] 7. Information on specialized medical institutions

[1596] The server will select an internal medicine clinic based on the electronic medical records and diagnosis results, and will also recommend a clinic that can provide mental care, taking into consideration Taro's concerns.

[1597] The server sends the medical institution information to the terminal and displays it to Taro.

[1598] Taro follows the instructions and makes a reservation.

[1599] 8. AI medical record handover

[1600] The server sends the electronic medical record to the clinic where the appointment is completed.

[1601] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[1602] In this way, incorporating an emotion engine makes it possible to provide a more personalized medical experience by responding to the user's emotional state in a more detailed manner.

[1603] The processing flow will be explained below.

[1604] Step 1:

[1605] Users launch the smartphone application and enter their symptoms by text or voice, for example, "I have a sore throat and a fever of 37.5 degrees."

[1606] Step 2:

[1607] The device receives the user's input information and simultaneously activates the emotion engine. The emotion engine analyzes the user's emotional state from the text and voice data entered. For example, it analyzes "anxiety" or "stress" from the words used and tone of voice when entering information.

[1608] Step 3:

[1609] The terminal transmits the analyzed emotion information and the symptom data of the user to the server.

[1610] Step 4:

[1611] The server analyzes the received symptom data and emotional information, passing the text data to a natural language processing (NLP) module to extract keywords such as "sore throat" and "fever," and then applies an initial diagnostic algorithm.

[1612] Step 5:

[1613] The server generates an initial diagnosis, for example, "suspected mild cold."

[1614] Step 6:

[1615] The server automatically generates additional questions taking into account emotional information. If the user is feeling anxious, the server softens the questions or provides detailed, easy-to-understand explanations. For example, it generates questions in the form of "Don't worry. Do you also have a cough or headache?"

[1616] Step 7:

[1617] The terminal displays the additional questions sent from the server to the user.

[1618] Step 8:

[1619] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[1620] Step 9:

[1621] The terminal transmits the user's response data to the server.

[1622] Step 10:

[1623] The server re-analyzes the additional responses and makes a final diagnosis, for example, a definitive diagnosis of "mild cold."

[1624] Step 11:

[1625] The server automatically generates an electronic medical record based on the user's symptoms, diagnosis results, and emotional information, and securely stores that information in a database.

[1626] Step 12:

[1627] The server selects medical institutions suitable for the user's area based on the generated electronic medical record and diagnosis results. Based on the emotional information, the server also provides additional information, such as clinics that can provide mental health care.

[1628] Step 13:

[1629] The server sends information about the selected medical institution to the terminal and provides the user with guidance, such as "The nearest internal medicine clinic is Hospital A. You can also receive mental health care there."

[1630] Step 14:

[1631] The user selects a medical institution based on the guidance and makes an appointment for a consultation.

[1632] Step 15:

[1633] The server securely transmits the user's electronic medical record and emotional information to the medical institution where the user has completed an appointment.

[1634] Step 16:

[1635] The medical institution's terminal receives the electronic medical record and emotional information sent from the server and prepares for treatment, ensuring smooth treatment when the patient arrives.

[1636] By going through these steps, users can receive prompt and appropriate medical services, and medical institutions can obtain detailed information in advance, resulting in more efficient medical treatment.In addition, the emotion engine enables flexible responses that take into account the user's psychological state.

[1637] Example 2

[1638] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1639] While conventional diagnostic systems can analyze a user's medical information and provide a diagnosis, they lack the ability to adjust the diagnostic process to take into account the user's emotional state, which can lead to users feeling stressed or anxious during the diagnosis process, resulting in a suboptimal medical experience.

[1640] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for a user to input medical information, a means for analyzing the input information, a means for generating an initial diagnosis based on the analysis results, a means for automatically generating additional questions, a means for recognizing the user's emotional state, a means for adjusting the diagnostic process based on the emotional state, a means for making a final diagnosis based on the user's answers, a means for generating an electronic medical record based on the final diagnosis result, a means for saving the generated electronic medical record and the diagnostic result, a means for guiding the user to an appropriate medical institution, and a means for transmitting the electronic medical record to the medical institution. This enables a detailed medical experience tailored to the user's emotional state, and more personalized medical care can be provided.

[1641] The term "user" refers to a person who uses this medical diagnostic system to input symptom information and the like.

[1642] "Medical information" refers to data entered by users regarding symptoms and health conditions.

[1643] "Emotional state" refers to the user's psychological reactions and feelings, including anxiety and stress about things.

[1644] "Means of analysis" refers to the techniques and algorithms used to process and analyze input data and extract meaningful information.

[1645] "Initial diagnosis result" refers to the first predicted diagnosis result obtained based on the input medical information.

[1646] "Means for automatically generating follow-up questions" refers to a technology or process that automatically generates follow-up questions to gather more detailed information based on the results of the initial diagnosis.

[1647] "Emotion engine" refers to the part of the system that includes the technology to recognize and analyze the user's emotional state from input data.

[1648] "Means for adjusting the diagnostic process" refers to technology for appropriately changing the diagnostic process and questions asked based on the user's emotional state.

[1649] "Final diagnosis" refers to a definitive diagnosis result obtained by analyzing all data, including the user's additional responses.

[1650] "Electronic Medical Record" means a medical record that stores a user's medical condition, diagnosis, and related information in digital form.

[1651] "Medical institution" refers to a facility such as a hospital or clinic that provides medical examinations and treatment.

[1652] "Natural language processing technology" refers to technology that allows computers to analyze, understand, and generate human language.

[1653] A "diagnostic algorithm" refers to a calculation procedure or method for making a diagnosis based on medical information.

[1654] A "generative AI model" refers to a model that uses artificial intelligence technology to generate new data and information.

[1655] The present invention provides a system that allows users to input medical information, analyzes that information, and provides diagnostic results. It also incorporates an emotion engine that recognizes the user's emotional state and adjusts the diagnostic process based on that information, thereby providing more appropriate and personalized medical treatment.

[1656] This system can be implemented using the following hardware and software. The hardware includes a smartphone or computer terminal for users to input medical information, and a server for analyzing data and generating diagnostic results. The software includes an AI chatbot app, an emotion engine, natural language processing (NLP) technology, and a diagnostic algorithm.

[1657] The specific system configuration and operation are as follows.

[1658] 1. User symptom input

[1659] Users use their smartphones or computers to input medical information into the AI ​​chatbot app, for example, "I have a sore throat and a slight fever."

[1660] 2. Recognizing emotional states

[1661] The device analyzes the user's input text (or voice) using an emotion engine, which uses NLP techniques and emotion analysis models to assess the user's emotional state, for example recognizing that the user is feeling anxious.

[1662] 3. Symptom analysis

[1663] The server uses NLP technology to analyze the symptom information and emotional state data received from the device. Specifically, it extracts keywords such as "sore throat" and "fever" and also analyzes the emotional information of "anxiety." This analysis uses a generative AI model and existing medical databases (e.g., Medline).

[1664] 4. Initial diagnosis and further questions

[1665] The server generates an initial diagnosis based on the analysis results. If the initial diagnosis is uncertain, the server automatically generates additional questions, such as "Do you have any other symptoms such as a cough or headache?" The questions are flexibly adjusted according to the patient's emotional state.

[1666] 5. Processing the User's Answers

[1667] The user answers the additional questions displayed on the terminal, for example, by typing "Yes, I have a slight cough."

[1668] 6. Final diagnosis and generation of electronic medical record

[1669] The server reanalyzes the user's additional answers and makes a final diagnosis, such as a "mild cold." It also generates and securely stores an electronic medical record based on the diagnosis.

[1670] 7. Medical Institution Information

[1671] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis. Taking into account the analysis results of the emotion engine, it also considers medical institutions that can provide psychological counseling and mental care. Information on appropriate medical institutions is sent to the terminal and directed to the user.

[1672] 8. AI medical record handover

[1673] The server securely transmits the electronic medical record to the medical institution where the user has made a reservation. The medical institution's terminal prepares for the medical treatment based on the received electronic medical record.

[1674] Specific examples

[1675] As an example, consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[1676] 1. User symptom input

[1677] Taro launches the app and types in, "I have a sore throat and a slight fever."

[1678] 2. Recognizing emotional states

[1679] The device analyzes the information Taro has entered and determines that he is feeling anxious.

[1680] 3. Symptom analysis

[1681] The server analyzes the received data using NLP technology and extracts keywords such as "sore throat," "fever," and "anxiety."

[1682] 4. Initial diagnosis and further questions

[1683] The initial diagnosis is "suspected cold," and a detailed follow-up question is automatically generated: "Do you have any other coughs or headaches?"

[1684] I'll present an additional question to Taro.

[1685] 5. Processing the User's Answers

[1686] Taro replies, "Yes, I have a slight cough."

[1687] 6. Final diagnosis and generation of electronic medical record

[1688] The server reanalyzes the additional responses and diagnoses the patient as having a mild cold. An electronic medical record is generated based on the diagnosis and stored securely.

[1689] 7. Medical Institution Information

[1690] Based on the electronic medical records and diagnosis results, the server will select an internal medicine clinic and also recommend a clinic that can provide mental care, taking into consideration Taro's anxiety.

[1691] Provide Taro with information about medical institutions.

[1692] 8. AI medical record handover

[1693] The server sends the medical record to the clinic where the reservation has been completed, and the medical institution prepares for treatment based on the received medical record.

[1694] As described above, the system of the present invention provides a detailed medical experience that is tailored to the user's emotional state, realizing personalized medical services.

[1695] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1696] Step 1: User symptom input

[1697] Users use their smartphones or computers to input medical information into the AI ​​chatbot app.

[1698] Example: "I have a sore throat and a slight fever."

[1699] Input: User's symptom information

[1700] Output: User input data stored on the device

[1701] Specific operation: Enter your symptoms into the app's input form and press the send button, and the data will be saved on your device.

[1702] Step 2: Recognizing your emotional state

[1703] The terminal analyzes the user's input text using an emotion engine.

[1704] The emotion engine uses NLP techniques and generative AI models to recognize emotions such as stress and anxiety.

[1705] Input: Text data entered by the user

[1706] Output: Emotional state (e.g., "anxiety")

[1707] Specific operation: The emotion engine analyzes the text and generates emotion tags. These tags are sent to the server.

[1708] Step 3: Symptom analysis

[1709] The server uses NLP technology to analyze the symptom information and emotional state data received from the device.

[1710] Keywords such as "sore throat" and "fever" are extracted, and analysis is performed including "anxiety." The generative AI model and medical databases (e.g., Medline) are referenced.

[1711] Input: Symptom information, emotional state data

[1712] Output: Initial diagnosis (e.g., "Suspected cold")

[1713] How it works: The NLP system extracts keywords, and the generative AI model references the medical database to generate an initial diagnosis.

[1714] Step 4: Initial diagnosis and further questions

[1715] The server generates an initial diagnosis based on the analysis results.

[1716] If the initial diagnosis is uncertain, a generative AI model is used to automatically generate follow-up questions, which are tailored based on the patient's emotional state.

[1717] Input: Analysis results (initial diagnosis)

[1718] Output: Initial diagnostic results and follow-up questions

[1719] Specific operation: The server performs an initial diagnosis, generates additional questions (e.g., "Do you have any other coughs or headaches?"), and sends the results to the device.

[1720] Step 5: Processing the user's answers

[1721] The user answers the additional questions displayed on the terminal.

[1722] For example, respond, "Yes, I have a slight cough."

[1723] Input: User's additional answer

[1724] Output: User response data saved on the device

[1725] Specific operation: When the user enters their answer into the app and presses the submit button, the data is saved on the device.

[1726] Step 6: Final diagnosis and electronic medical record generation

[1727] The server reanalyzes the user's additional answers and makes a final diagnosis.

[1728] A final diagnosis is determined using generative AI models and medical databases.

[1729] Input: Additional user answers, initial diagnosis results

[1730] Output: Final diagnosis (e.g., "Mild cold"), electronic medical record

[1731] Specific operation: The server analyzes the additional answers, makes a final diagnosis, and automatically generates and saves the results in the electronic medical record.

[1732] Step 7: Referral to a medical institution

[1733] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[1734] Taking into account the analysis results of the emotion engine, we will also consider medical institutions that can provide psychological counseling and mental care.

[1735] Input: Electronic medical records, final diagnosis results

[1736] Output: Appropriate medical institution information

[1737] Specific operation: The server selects a medical institution, sends information about the appropriate medical institution to the terminal, and guides the user.

[1738] Step 8: AI medical record handover

[1739] The server securely transmits the electronic medical record to the medical institution where the user has completed the reservation.

[1740] The medical institution's terminal prepares for medical treatment based on the received electronic medical record.

[1741] Input: Reservation information, electronic medical record

[1742] Output: Medical record data stored on the medical institution's terminal

[1743] Specific operation: The medical record is electronically sent from the server to the medical institution's terminal, and the medical institution prepares for treatment based on that information.

[1744] (Application example 2)

[1745] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1746] In autonomous vehicles, it is necessary for passengers and drivers to be able to quickly and accurately grasp their own health status and take necessary measures. In particular, for health-related input information, which is often influenced by emotional states, it is necessary to provide more appropriate and personalized medical assistance by recognizing emotions and adjusting the diagnostic process based on those emotions. However, with conventional systems, it has been difficult to integrate emotion recognition and health examinations and provide route guidance to the nearest medical institution in an emergency in cooperation with autonomous vehicles. These challenges must be resolved.

[1747] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1748] In this invention, the server includes means for recognizing the emotional state of the user, means for adjusting the diagnostic process based on the recognized emotional state, means for selecting and providing guidance to a medical institution according to the emotional state, and means for providing guidance on a route to the nearest medical institution in cooperation with the self-driving vehicle in an emergency. This enables a medical treatment process that takes the user's emotional state into consideration, and by cooperating with the self-driving vehicle, it is possible to respond quickly and appropriately in an emergency.

[1749] "User" refers to the passengers and drivers who use the system's health check function.

[1750] "Medical information" refers to all information entered by the user regarding health conditions, symptoms, and past medical history.

[1751] "Input means" refers to an interface that allows users to provide medical information to the system by voice or text. Examples include touch panels and voice recognition systems.

[1752] "Means of analysis" refers to technology that analyzes the medical information entered by the user and converts it into useful data. Natural language processing (NLP) technology is one example.

[1753] "Means for generating an initial diagnosis" refers to algorithms or techniques that generate an initial diagnosis based on the analyzed information.

[1754] "Means for automatically generating additional questions" refers to a technology that automatically creates questions necessary for further diagnosis when the initial diagnosis result is inconclusive.

[1755] The "means for making a final diagnosis" refers to a technology for determining the final results of a health check based on the user's answers to additional questions.

[1756] "Means for generating an electronic medical record" refers to a technology that creates a patient's medical record in electronic form based on the final diagnosis.

[1757] "Means for storing medical records and diagnostic results" refers to technology for securely storing the generated electronic medical records and diagnostic results in a database or cloud service.

[1758] "Means for guiding users to appropriate medical institutions" refers to a technology that suggests medical institutions that can provide appropriate medical services to users based on the final diagnosis results.

[1759] "Means for transmitting electronic medical records to medical institutions" refers to technology for securely transmitting the generated electronic medical records to the medical institution selected by the user.

[1760] "Means for recognizing emotional states" refers to technology that analyzes a user's emotional state using text, audio, and video input by the user.

[1761] "Means for adjusting the diagnostic process" refers to technology that tailors the content of the diagnosis or interview to suit the user based on the recognized emotional state.

[1762] "Means for selecting and providing guidance to medical institutions according to emotional state" refers to technology that selects a medical institution based on the results of analyzing the user's emotional state, taking into consideration appropriate mental care.

[1763] "Means of working with autonomous vehicles to provide route guidance to the nearest medical facility in an emergency" refers to technology that works with the navigation system of an autonomous vehicle to provide an emergency route to the most appropriate medical facility when a serious health problem is detected.

[1764] The present invention is a system that integrates health checkups and emotion recognition within an autonomous vehicle, enabling tailored responses to the user's health condition. In particular, it includes a means for recognizing the user's emotional state and adjusting the diagnostic process accordingly, and a means for linking the autonomous vehicle with the vehicle in an emergency to provide route guidance to the nearest medical facility.

[1765] Program Overview

[1766] The server, terminal, and user work together to perform the following processes.

[1767] User health information input

[1768] The user inputs medical information using the autonomous vehicle's touchscreen or voice input system. For example, the user might input, "I have chest pain and difficulty breathing." This input information is immediately transmitted to the server.

[1769] emotion recognition

[1770] When a user enters health information, the device uses a camera and microphone to analyze the user's facial expressions and voice to recognize their emotional state. An emotion recognition engine (e.g., Affectiva) is used to evaluate emotional states such as tension and fear.

[1771] Symptom analysis and early diagnosis

[1772] The server analyzes the input health information and emotion recognition data using natural language processing (NLP) technology. Specifically, it uses an NLP engine such as Google Cloud Natural Language to make an initial diagnosis based on the information such as "chest pain and difficulty breathing" and emotion data such as "tension" and "fear."

[1773] Generate follow-up questions

[1774] If the initial diagnosis is uncertain, the server generates follow-up questions, taking into account the perceived emotional state and generating softer, gentler questions, such as "Have you been feeling stressed lately?" or "Have you had similar symptoms in the past?"

[1775] User responses and final diagnosis

[1776] Once the user answers the additional questions, the server performs another analysis and makes a final diagnosis. The analysis is performed using a diagnostic algorithm (e.g., IBM Watson Health), and the final diagnosis is, for example, "mild cardiac abnormality."

[1777] Electronic medical record generation and storage

[1778] The server automatically generates and securely stores electronic medical records based on the final diagnosis results in a database or cloud storage.

[1779] Medical institution information

[1780] The server then guides the user to an appropriate medical institution based on the final diagnosis and emotional state. For example, if tension or fear is detected, it will recommend a medical institution that also provides mental care. Furthermore, if the situation is urgent, it will work with the autonomous vehicle's navigation system to automatically set a route to the nearest medical institution.

[1781] Specific examples

[1782] scenario

[1783] When a user enters "I have chest pain and difficulty breathing" in the car, the system uses an emotion recognition engine to detect emotions such as "tension" and "fear." As a result, the server performs an initial diagnosis, displays additional questions as necessary, and makes a final diagnosis. An electronic medical record is then generated and securely stored. In an emergency, the system works in conjunction with the autonomous vehicle's navigation system to provide route guidance to the nearest medical facility.

[1784] Prompt Sentence Examples

[1785] User: "My chest hurts and I'm having trouble breathing."

[1786] Emotional state: tension, fear

[1787] Initial diagnosis: Possible heart problem

[1788] Additional questions:

[1789] - "Have you been feeling stressed lately?"

[1790] - "Have you had similar symptoms in the past?"

[1791] Emergency Response:

[1792] - "This is likely an emergency, so we will escort you to the nearest medical facility. Please remain calm and wait."

[1793] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1794] Step 1:

[1795] User enters medical information

[1796] Input: The user inputs information about their health status using a touchscreen or voice recognition system inside the autonomous vehicle.

[1797] Action: The user types or speaks a symptom, such as "I have chest pain and difficulty breathing."

[1798] Output: The input information is stored as digital data on the terminal and sent to the server.

[1799] Step 2:

[1800] The device performs emotion recognition

[1801] Input: Health information, facial and voice data entered by the user.

[1802] How it works: It uses the camera and microphone to analyze the user's facial expressions and voice, and uses an emotion recognition engine (e.g., Affectiva) to assess their emotional state.

[1803] Output: The recognized emotional state (e.g., tension or fear) is sent as data from the device to the server.

[1804] Step 3:

[1805] The server analyzes health information and emotional data.

[1806] Input: User health and emotional state data.

[1807] How it works: The server uses natural language processing (NLP) technology (e.g., Google Cloud Natural Language) to analyze the health information entered and integrate it with emotional data.

[1808] Output: An initial diagnosis (e.g., possible cardiac issues) is generated as a result of the analysis.

[1809] Step 4:

[1810] The server generates a follow-up question

[1811] Input: Initial diagnosis and emotional state data.

[1812] How it works: Based on the initial diagnosis result, if the diagnosis is uncertain, the server generates soft questions depending on the emotional state.

[1813] Output: Follow-up questions (e.g., "Have you been feeling stressed lately?", "Have you had similar symptoms in the past?") are displayed to the chatbot.

[1814] Step 5:

[1815] The user answers additional questions

[1816] Input: The user's answer to the follow-up question.

[1817] What it does: The user types a response such as "Yes, it's stressful" or "No, this is the first time I've experienced something like this."

[1818] Output: The user's answers are stored digitally on the device and sent to the server.

[1819] Step 6:

[1820] The server makes the final diagnosis and generates the electronic medical record.

[1821] Input: Additional user answers and analytics data.

[1822] How it works: The server re-analyzes the data using a diagnostic algorithm (e.g., IBM Watson Health) to make a final diagnosis, automatically generates an electronic medical record based on the results, and securely stores the generated electronic medical record and the diagnosis results in a database.

[1823] Output: Final diagnosis (e.g., "Minor cardiac abnormality") and generated electronic medical record.

[1824] Step 7:

[1825] The server guides users to the appropriate medical institution.

[1826] Input: Final diagnosis and electronic medical record.

[1827] How it works: The server selects the most appropriate medical institution for the user based on the diagnosis results and emotional state, and works with the navigation system in the autonomous vehicle to provide directions to the appropriate medical institution.

[1828] Output: Medical facility information and route directions are displayed on the device.

[1829] Step 8:

[1830] Autonomous vehicles provide route guidance

[1831] Input: Route information to the selected medical facility.

[1832] How it works: The autonomous vehicle's navigation system creates an optimal route for the user and automatically guides the vehicle to a medical facility.

[1833] Output: The car will start driving automatically according to the optimal route and the user will reach the destination safely.

[1834] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1835] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1836] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1837] [Fourth embodiment]

[1838] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1839] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1840] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1841] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1842] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1843] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1844] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1845] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1846] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1847] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1848] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1849] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1850] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1851] The present invention is a system that allows a user to input medical information, analyzes the information, and provides a diagnosis. How the system operates and how it is specifically implemented will be described below.

[1852] Main processing of the program

[1853] 1. User symptom input

[1854] Users use devices such as smartphones or computers to input medical information into the AI ​​chatbot app.

[1855] For example, a user can input "I have a sore throat and a slight fever," and this information is sent to the server via the terminal.

[1856] 2. Symptom analysis

[1857] The server analyzes the symptom information received from the terminal using natural language processing (NLP) technology.

[1858] The server extracts keywords such as "sore throat" and "fever" and applies an initial diagnostic algorithm to identify potential diagnoses.

[1859] 3. Presenting the initial diagnosis and asking follow-up questions

[1860] The server generates an initial diagnosis based on the analysis results.

[1861] If the initial diagnosis is inconclusive, the server automatically generates additional questions and displays them to the user via the terminal.

[1862] The user answers the follow-up questions and sends, for example, "Yes, I have a slight cough."

[1863] 4. Final diagnosis and medical record generation

[1864] The server re-analyzes the additional answers and determines the final diagnosis, for example, a "mild cold."

[1865] The server automatically generates and securely stores electronic medical records containing the user's medical condition and diagnosis results.

[1866] 5. Information on specialized medical institutions

[1867] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[1868] The server transmits information about appropriate medical institutions to the terminal and provides guidance to the user.

[1869] The user can visit a medical institution based on the guidance.

[1870] 6. AI medical record handover

[1871] The server securely transmits the electronic medical record to the selected medical institution.

[1872] The medical institution's terminal prepares for medical treatment based on the received electronic medical record.

[1873] This allows the user to receive medical treatment smoothly.

[1874] Specific examples

[1875] scenario

[1876] Consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[1877] 1. User symptom input

[1878] The user (Taro) launches the app and enters, "I have a sore throat and a slight fever."

[1879] The terminal transmits this input information to the server.

[1880] 2. Symptom analysis

[1881] The server uses natural language processing to extract keywords such as "sore throat" and "fever" from the received information, and considers the possibility of a cold in the initial diagnosis.

[1882] 3. Presenting the initial diagnosis and asking follow-up questions

[1883] The server generates an initial diagnosis and determines that the patient "may have a cold."

[1884] To obtain additional information, the server generates a question, "Do you have a cough or headache?", and displays it on the device.

[1885] The user (Taro) responds, "Yes, I have a slight cough."

[1886] 4. Final diagnosis and medical record generation

[1887] The server reanalyzes the additional answers and determines the final diagnosis as "a mild cold."

[1888] The server generates an electronic medical record based on the diagnosis results and stores it securely.

[1889] 5. Information on specialized medical institutions

[1890] The server selects a nearby internal medicine clinic based on the electronic medical records and diagnosis results.

[1891] The server sends information about recommended medical institutions to the terminal and displays it to Taro.

[1892] The user (Taro) makes a reservation by following the instructions.

[1893] 6. AI medical record handover

[1894] The server sends the electronic medical record to the clinic where the appointment is completed.

[1895] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[1896] In this way, the present invention provides users with prompt and appropriate medical services and improves the efficiency of medical treatment at medical institutions.

[1897] The processing flow will be explained below.

[1898] Step 1:

[1899] Users launch the smartphone application and enter their symptoms by text or voice, for example, "I have a sore throat and a fever of 37.5 degrees."

[1900] Step 2:

[1901] The terminal receives the user's input information and transmits the text data to the server.

[1902] Step 3:

[1903] The server passes the received text data to a natural language processing (NLP) module to extract symptom keywords, such as "sore throat" and "fever."

[1904] Step 4:

[1905] The server applies an initial diagnosis algorithm based on the extracted keywords to generate an initial diagnosis result, for example, determining that there is a high possibility of a cold.

[1906] Step 5:

[1907] If the initial diagnosis result does not provide sufficient definitive information, the server automatically generates additional questions, such as "Do you have a cough or headache?"

[1908] Step 6:

[1909] The terminal displays the additional questions sent from the server to the user.

[1910] Step 7:

[1911] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[1912] Step 8:

[1913] The terminal transmits the user's additional responses to the server.

[1914] Step 9:

[1915] The server re-analyzes the additional responses and makes a final diagnosis, for example, a "mild cold."

[1916] Step 10:

[1917] The server automatically generates an electronic medical record based on the user's medical condition and diagnosis results, and securely stores that information in a database.

[1918] Step 11:

[1919] The server selects an appropriate medical institution in the user's area based on the final diagnosis and the generated electronic medical record.

[1920] Step 12:

[1921] The server sends information about the selected medical institution to the terminal and provides the user with guidance, such as "The nearest internal medicine clinic is Hospital A."

[1922] Step 13:

[1923] The user checks the information about the medical institution provided by the server and makes an appointment for a medical examination.

[1924] Step 14:

[1925] The server securely transmits the user's electronic medical record to the medical institution where the user has completed an appointment.

[1926] Step 15:

[1927] The medical institution's terminal receives the electronic medical records sent from the server and prepares for treatment, ensuring smooth treatment when the patient arrives.

[1928] In this way, the system of the present invention provides a seamless process from the user's symptom input to a final diagnosis and guidance to an appropriate medical institution, thereby streamlining medical access.

[1929] Example 1

[1930] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1931] There is a need for systems that allow users to input medical information, analyze that information appropriately, and provide a fast and accurate diagnosis, as well as automate the process of directing patients to appropriate medical institutions based on the diagnosis results and the safe transfer of electronic medical records. Furthermore, because conventional systems have difficulty selecting a medical institution appropriate for the user's area and improving the accuracy of diagnosis results, new technologies are needed to improve the quality of medical services.

[1932] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1933] In this invention, the server includes means for a user to input medical information, means for analyzing the input information, means for generating an initial diagnosis based on the analysis results, means for automatically generating additional questions, means for making a final diagnosis based on the user's answers, means for generating an electronic medical record based on the final diagnosis, means for saving the generated electronic medical record and the diagnosis results, means for directing the user to an appropriate medical institution, means for transmitting the electronic medical record to the medical institution, means for selecting a medical institution suitable for the user's area based on the electronic medical record and the diagnosis results, and means for securely transmitting the electronic medical record to the selected medical institution. This allows the user to receive a quick and accurate diagnosis, and enables directing to an appropriate medical institution and handing over the diagnosis results.

[1934] 1. "User" refers to a person who inputs medical information and receives diagnosis results and guidance on medical institutions.

[1935] 2. "Means for inputting information" means a device or interface used by a user to input medical information.

[1936] 3. "Means for analyzing information" refers to a system that uses data processing technology to analyze input information, extract keywords, and perform initial diagnosis.

[1937] 4. "Means for generating an initial diagnosis" means an algorithm or process that generates a preliminary diagnosis based on the analyzed information.

[1938] 5. "Means for automatically generating additional questions" refers to a system that automatically generates questions to obtain additional information necessary to improve the accuracy of initial diagnostic results.

[1939] 6. "Means for making a final diagnosis" means a system or process that reanalyzes the user's additional responses and determines a final diagnosis.

[1940] 7. "Means for generating electronic medical records" refers to a system that automatically creates electronic medical records that record diagnostic results and the user's medical condition.

[1941] 8. "Means for storing diagnostic results" means a system that stores the generated electronic medical records and diagnostic results in secure and reliable storage.

[1942] 9. "Means for guiding users to medical institutions" refers to a system that selects a medical institution suitable for the user based on the diagnosis results and provides that information to the user.

[1943] 10. "Means for transmitting electronic medical records" means the communications process and infrastructure for securely transmitting the generated electronic medical records to the selected healthcare provider.

[1944] 11. "Means for selecting a medical institution suitable for the area" refers to a system that selects the most suitable facility from local medical institutions based on the user's location information and diagnosis results.

[1945] 12. "Means for securely transmitting electronic medical records" means a system or protocol for transmitting electronic medical records to a medical institution using security such as encrypted communications.

[1946] This invention is a system in which a user inputs medical information, analyzes that information, and provides a diagnosis. The system is basically composed of a terminal, a server, and a medical institution's terminal. Each component of the system and its specific operation are described below.

[1947] Terminal

[1948] The terminal refers to a device such as a smartphone or PC that users use to input medical information. Specifically, they perform the following operations:

[1949] The user launches the application and enters information about their symptoms or illnesses.

[1950] For example, you might type, "I have a sore throat and a slight fever." This information is sent over the internet to a server.

[1951] server

[1952] The server is the main part that analyzes the information received from the user and generates the diagnosis results. The server uses the following hardware and software:

[1953] Hardware: Server equipment equipped with a high-performance CPU, sufficient memory, SSD storage, etc.

[1954] Software: TensorFlow and Spacy for natural language processing (NLP) techniques, MySQL for database management systems (DBMS), Scikit-learn and TensorFlow for diagnostic algorithms.

[1955] The operation of the server is as follows.

[1956] The information sent from the terminal is first stored in a database.

[1957] Next, an NLP model using TensorFlow and Spacy analyzes the input information and extracts keywords such as "sore throat" and "fever."

[1958] Based on the extracted keywords, an initial diagnosis algorithm (Scikit-learn or TensorFlow) is applied to generate initial diagnosis results.

[1959] If the initial diagnosis is uncertain, the server automatically generates additional questions and sends them to the terminal.

[1960] If the user answers additional questions, the information is sent back to the server for reanalysis.

[1961] Once the final diagnosis is confirmed, an electronic medical record is automatically generated and securely stored in an AWS S3 bucket or similar.

[1962] Based on the diagnosis results and electronic medical records, the system selects a medical institution suitable for the user's area. For example, it uses the Google Maps API to search for nearby medical institutions.

[1963] Medical institution terminals

[1964] The medical institution's terminal is a device for providing medical treatment based on the received electronic medical records.

[1965] Electronic medical records sent from the server are transmitted using encryption technology such as SSL / TLS.

[1966] The medical institution's terminal receives the electronic medical record, and medical staff prepare for treatment.

[1967] Specific examples

[1968] For example, if a user experiences cold-like symptoms, the system operates as follows.

[1969] 1. User symptom input

[1970] The user launches the app and types, "I have a sore throat and a slight fever."

[1971] The terminal sends this information to the server.

[1972] 2. Symptom analysis

[1973] The server uses NLP to extract keywords such as "sore throat" and "fever" from the received information, and considers the possibility of a cold in the initial diagnosis.

[1974] 3. Presenting the initial diagnosis and asking follow-up questions

[1975] The server generates an initial diagnosis of "suspected cold."

[1976] To get additional information, the server generates a question, "Do you have a cough or headache?", and displays it on the device.

[1977] The user responds, "Yes, I have a slight cough."

[1978] 4. Final diagnosis and medical record generation

[1979] The server reanalyzes the additional answers and determines the final diagnosis as "mild cold."

[1980] The server generates an electronic medical record based on the diagnosis results and stores it securely.

[1981] 5. Information on specialized medical institutions

[1982] Based on the electronic medical records and diagnosis results, the server selects a nearby internal medicine clinic and sends the information to the terminal.

[1983] The user makes a reservation by following the instructions.

[1984] 6. AI medical record handover

[1985] The server sends the electronic medical record to the clinic where the reservation is completed.

[1986] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[1987] Example prompts to input to the generative AI model

[1988] Example 1: "Describe a program that analyzes symptom information entered by a user and selects the most appropriate medical institution."

[1989] Example 2: "Given a patient's sore throat and mild fever, detail the process of using NLP to generate an initial diagnosis and follow-up questions, and then storing the final diagnosis in the electronic medical record."

[1990] This system provides users with accurate and prompt medical services, significantly improving the efficiency of medical treatment at medical institutions.

[1991] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1992] Step 1:

[1993] User symptom input

[1994] Users use their smartphones or computers to input symptom information into the AI ​​chatbot app, such as "sore throat" and "mild fever."

[1995] Specific behavior:

[1996] The user launches the app and enters "I have a sore throat and a slight fever" into the symptom entry form.

[1997] After entering the information, press the send button.

[1998] Input: Symptom information entered by the user.

[1999] Output: The device sends the input information to the server.

[2000] Step 2:

[2001] Symptom analysis

[2002] The server receives the symptom information sent from the device and analyzes it using natural language processing (NLP) technology. Specifically, it uses TensorFlow and Spacy to extract keywords such as "sore throat" and "fever" from the text data.

[2003] Specific behavior:

[2004] The server stores the received symptom data in a database.

[2005] An NLP model analyzes the data and extracts keywords.

[2006] Input: Symptom information received by the server.

[2007] Output: Extracted keywords "sore throat" and "fever".

[2008] Step 3:

[2009] Generate an initial diagnosis

[2010] Based on the extracted keywords, the server applies an initial diagnostic algorithm (using Scikit-learn or TensorFlow) to generate provisional diagnostic results.

[2011] Specific behavior:

[2012] The server runs an algorithm to provide an initial diagnosis corresponding to the symptoms.

[2013] The initial diagnosis result is "suspected cold."

[2014] Input: Extracted keywords.

[2015] Output: Initial diagnosis: "Suspected cold."

[2016] Step 4:

[2017] Generate and present follow-up questions

[2018] If the initial diagnosis is inconclusive, the server automatically generates additional questions and presents them to the user via the terminal, who then answers the questions.

[2019] Specific behavior:

[2020] The server generates follow-up questions based on the initial diagnostic results.

[2021] An additional question, "Do you have a cough or headache?", is generated and sent to the device.

[2022] The user receives the question and responds, "Yes, I have a slight cough."

[2023] Input: Initial diagnosis and follow-up questions.

[2024] Output: User answers "Yes, I have a slight cough."

[2025] Step 5:

[2026] Confirmation of final diagnosis and creation of medical records

[2027] The server reanalyzes the user's additional answers and determines the final diagnosis, which is a "mild cold." It also automatically generates and saves an electronic medical record based on the final diagnosis.

[2028] Specific behavior:

[2029] The server re-analyzes the additional answers and applies the final diagnostic algorithm.

[2030] The final diagnosis is confirmed as "mild cold."

[2031] Generate and securely store electronic medical records.

[2032] Input: The user's additional answer.

[2033] Output: Final diagnosis and electronic medical record.

[2034] Step 6:

[2035] Guide to specialized medical institutions

[2036] Based on the final diagnosis, the server selects a medical institution suitable for the user's area and sends that information to the terminal to guide the user.

[2037] Specific behavior:

[2038] The server uses Google Maps APIs and other tools to search for nearby medical institutions based on the user's location information.

[2039] Information on the appropriate medical institution is selected and sent to the terminal.

[2040] The user checks the information and makes a reservation.

[2041] Input: Electronic medical record and final diagnosis.

[2042] Output: Information on selected medical institutions.

[2043] Step 7:

[2044] AI medical record handover

[2045] The server securely transmits the electronic medical record to the selected medical institution, and the medical institution's terminal prepares for treatment based on the received electronic medical record.

[2046] Specific behavior:

[2047] The server transmits the electronic medical record to the medical institution using a secure communication channel (e.g., SSL / TLS).

[2048] The medical institution's terminal receives the electronic medical records and imports them into the system.

[2049] Medical staff prepare for treatment based on electronic medical records.

[2050] Input: Stored electronic medical record.

[2051] Output: Electronic medical records sent to the medical institution's terminal.

[2052] The above is a detailed description of the operation of each processing step of this system.

[2053] (Application example 1)

[2054] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2055] In today's world, accessing immediate health advice and medication recommendations in brick-and-mortar stores often requires the intervention of a medical professional. However, contacting a medical professional can be time-consuming, and the information needed to select the appropriate medication is often lacking. Furthermore, when additional medical information is required, the response can be delayed. Thus, providing prompt and appropriate health advice in brick-and-mortar stores presents a challenge.

[2056] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2057] In this invention, the server includes means for a user to input health information, means for analyzing the input information, means for generating an initial diagnosis based on the analysis results, means for automatically generating additional questions, means for making a final diagnosis based on the user's answers, means for generating an electronic medical record based on the final diagnosis results, means for saving the generated electronic medical record and the diagnosis results, means for guiding the user to an appropriate medical facility, means for transmitting the electronic medical record to the medical facility, means for presenting recommended medicines based on the final diagnosis results, and means for notifying a specialist if the user requests a detailed explanation. This enables users to receive prompt and appropriate health advice in a physical store.

[2058] A "user" is an individual who uses the system and inputs health information.

[2059] A "healthcare facility" is a place that provides healthcare services, such as a hospital, doctor's office, or clinic.

[2060] "Health-related information" refers to information related to the user's health condition, such as symptoms, medical history, and physical condition.

[2061] "Analysis" refers to processing health information and converting it into meaningful data.

[2062] The "initial diagnosis result" is a preliminary diagnosis result based on information input by the user.

[2063] "Additional questions" are questions automatically generated by the system to complement the initial diagnosis results.

[2064] The "final diagnosis" is a definitive diagnosis result based on the user's answers.

[2065] An "electronic medical record" is a record of a user's health information and diagnostic results stored in digital format.

[2066] "Preservation" refers to the safe and proper storage of generated data.

[2067] A "drug" is a substance intended to treat or prevent a disease or improve symptoms.

[2068] An "expert" is an individual who has knowledge of health information and pharmaceuticals and is qualified to provide detailed explanations to users.

[2069] A "server" is a computer that processes information from users and controls the entire system.

[2070] "Recommending" means presenting the best option.

[2071] "Notification" refers to an announcement that a particular action should be taken.

[2072] Overall system picture

[2073] The present invention is a system that allows users to input health information, analyzes the information, and provides diagnostic results and recommended medicines. How the system works and how it is implemented will be described below.

[2074] Hardware and software used

[2075] Hardware: Smartphones, tablets, servers

[2076] Software: Natural language processing technology (spacy), question answering models (transformers)

[2077] Processing flow

[2078] The system of this invention is mainly composed of three entities (user, terminal, and server). Each entity functions as follows:

[2079] 1. User information entry and submission

[2080] Users enter health information into the system via their smartphone or tablet. For example, they enter information like, "I have a sore throat and a slight fever." The entered information is sent from the device to the server.

[2081] 2. Information analysis by the server

[2082] The server uses natural language processing technology (spacy) to analyze the information sent by the user. Specifically, it extracts keywords such as "sore throat" and "fever" and generates an initial diagnosis based on these.

[2083] 3. Additional questions and diagnosis confirmation by the server

[2084] If the initial diagnosis is uncertain, the server uses a question-answering model (transformers) to automatically generate follow-up questions, such as "Do you have a cough or a headache?", and presents them to the user via the device. Once the user answers the follow-up questions, the information is reanalyzed to determine the final diagnosis.

[2085] 4. Generating and storing electronic medical records

[2086] Based on the final diagnosis, the server generates an electronic medical record, which contains the user's health information and diagnosis results and is securely stored.

[2087] 5. Presentation of recommended medications

[2088] Based on the final diagnosis, the server will recommend medicines to the user. For example, for a mild cold, it will display a list of medicines such as "Cold Medicine A" and "Cold Medicine B."

[2089] 6. Notice to Experts

[2090] If the user requests further explanation, the server will notify a specialist to provide further care to the user, allowing the user to receive prompt and appropriate health advice while in a physical store.

[2091] Specific examples

[2092] scenario:

[2093] The user types "I have a sore throat and a slight fever" into their smartphone.

[2094] The server generates a follow-up question: "Do you have a cough or a headache?", to which the user responds: "Yes, I have a slight cough."

[2095] The final diagnosis is a "mild cold," and "cold medicine A" or "cold medicine B" is recommended.

[2096] Prompt Sentence Examples

[2097] "When a user enters 'I have a sore throat and a slight fever,' please generate a program that displays the follow-up question 'Do you have a cough or a headache?'"

[2098] The above is a specific description of the "Mode for Carrying Out the Invention." As a result, the present invention provides users with prompt and appropriate health advice, thereby improving service at physical stores.

[2099] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2100] Step 1:

[2101] The user enters health information.

[2102] Input: Text information about the user's symptoms or health condition (e.g., "I have a sore throat and a slight fever").

[2103] Specific operation: The user uses a smartphone or tablet device to enter health information into the application and press the send button.

[2104] Output: The entered text information is sent to the server via the terminal.

[2105] Step 2:

[2106] The server analyzes the information it receives.

[2107] Input: Submitted text information about the user's health.

[2108] Data processing / calculation: The server uses natural language processing technology (spacy) to analyze the text and extract keywords such as "sore throat" and "fever."

[2109] Specific operation: The NLP model on the server analyzes the input text and extracts keywords related to the symptoms.

[2110] Output: A list of extracted keywords is generated.

[2111] Step 3:

[2112] The server generates an initial diagnosis.

[2113] Input: Extracted keyword list.

[2114] Data processing / calculation: The server applies a diagnostic algorithm and makes an initial diagnosis based on keywords.

[2115] How it works: An algorithm within the server evaluates the keyword list and generates an initial diagnosis, such as "suspected cold."

[2116] Output: An initial diagnostic result is generated and sent to the next step.

[2117] Step 4:

[2118] The server automatically generates additional questions.

[2119] Input: Initial diagnostic results.

[2120] Data transformation / computation: Question-answering models (transformers) are used to generate follow-up questions to complement the initial diagnostic results.

[2121] How it works: The AI ​​model in the server generates follow-up questions based on the initial diagnosis, such as "Do you have a cough or headache?"

[2122] Output: Generated follow-up questions are sent to the terminal.

[2123] Step 5:

[2124] The user answers additional questions.

[2125] Input: A follow-up question sent by the server.

[2126] Specific operation: The user checks the additional questions on a smartphone or tablet and enters an answer such as "Yes, I have a slight cough."

[2127] Output: The user's answer is sent to the server via the terminal.

[2128] Step 6:

[2129] The server performs the final diagnosis.

[2130] Input: The user's additional answer.

[2131] Data processing / calculation: The server reanalyzes the additional answers and determines the final diagnosis.

[2132] Specific operation: A diagnostic algorithm in the server comprehensively evaluates all the user's input data and generates a final diagnosis result such as "mild cold."

[2133] Output: The final diagnostic results are generated.

[2134] Step 7:

[2135] The server generates the electronic medical record.

[2136] Input: Final diagnosis and user health information.

[2137] Data processing / calculation: The server automatically generates the user's electronic medical record based on the final diagnosis results.

[2138] Specific operation: A program on the server combines diagnostic results and user information to create an electronic medical record.

[2139] Output: The generated electronic medical record is stored in a database.

[2140] Step 8:

[2141] The server presents recommended medications.

[2142] Input: Final diagnosis result.

[2143] Data processing / calculation: The server generates a list of recommended medicines based on the final diagnosis results.

[2144] Specific operation: The system within the server analyzes the diagnostic results and creates a list of relevant medications.

[2145] Output: A list of recommended medications is sent to the terminal.

[2146] Step 9:

[2147] Notify the expert.

[2148] Input: User's detailed description request.

[2149] Data processing / calculation: The server sends a notification to the expert.

[2150] Specific operation: The system in the server notifies the expert of the user's request for a detailed explanation.

[2151] Output: A notification is sent to the expert.

[2152] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2153] The present invention provides a system that allows users to input medical information, analyzes that information, and provides diagnostic results, and also incorporates an emotion engine that recognizes the user's emotional state and adjusts the diagnostic process based on that information, thereby providing more appropriate and personalized medical treatment. Below, we will explain how the system works and how it is specifically implemented.

[2154] Main processing of the program

[2155] 1. User symptom input

[2156] Users use devices such as smartphones or computers to input medical information into the AI ​​chatbot app.

[2157] For example, a user can input "I have a sore throat and a slight fever," and this information is sent to the server via the terminal.

[2158] 2. Recognizing emotional states

[2159] When a user inputs information through text or voice, the device uses an emotion engine to analyze the user's emotional state.

[2160] The emotion engine analyzes input text and voice and evaluates emotions such as whether the user is feeling stressed or anxious.

[2161] 3. Symptom analysis

[2162] The server analyzes the symptom information and emotional state data received from the device using natural language processing (NLP) technology.

[2163] The server analyzes keywords such as "sore throat" and "fever," as well as emotional information such as "anxiety" and "stress."

[2164] 4. Presenting the initial diagnosis and asking follow-up questions

[2165] The server generates an initial diagnosis based on the analysis results.

[2166] If the initial diagnosis is inconclusive, the server automatically generates additional questions.

[2167] Depending on the user's emotional state, for example, if the user is feeling stressed, the questions are softened or the explanations are made more detailed.

[2168] The terminal displays the additional questions sent from the server to the user.

[2169] 5. User Responses

[2170] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[2171] 6. Final diagnosis and medical record generation

[2172] The server re-analyzes the additional answers and provides a final diagnosis, for example, "a mild cold."

[2173] The server automatically generates an electronic medical record based on the user's medical condition and diagnosis results, and securely stores that information in a database.

[2174] 7. Information on specialized medical institutions

[2175] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis results.

[2176] Based on the analysis results of the emotion engine, users with high levels of stress or anxiety will receive individual support, such as being directed to medical institutions that can provide psychological counseling and mental care.

[2177] The server transmits information about appropriate medical institutions to the terminal and provides guidance to the user.

[2178] 8. AI medical record handover

[2179] The server securely transmits the user's electronic medical record to the medical institution where the user has completed an appointment.

[2180] The medical institution's terminal will then prepare for treatment based on the received electronic medical records, ensuring smooth treatment when the patient arrives.

[2181] Specific examples

[2182] scenario

[2183] Consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[2184] 1. User symptom input

[2185] The user (Taro) launches the app and enters, "I have a sore throat and a slight fever."

[2186] The terminal transmits this input information to the server.

[2187] 2. Recognizing emotional states

[2188] While the user is typing, the device uses an emotion engine to analyze Taro's emotional state and assesses that he is feeling "anxious."

[2189] 3. Symptom analysis

[2190] The server uses natural language processing to extract keywords such as "sore throat" and "fever" from the received data, and also performs an initial diagnosis by incorporating emotional information such as "anxiety."

[2191] 4. Presenting the initial diagnosis and asking follow-up questions

[2192] The server generates an initial diagnosis of "suspected cold."

[2193] To ease the user's anxiety, a follow-up question with detailed and gentle explanations is automatically generated: "Are you experiencing any other coughs or headaches?"

[2194] The terminal displays the question to Taro.

[2195] 5. User Responses

[2196] The user (Taro) responds, "Yes, I have a slight cough."

[2197] 6. Final diagnosis and medical record generation

[2198] The server reanalyzes the additional responses, makes a final diagnosis of "mild cold," and generates and securely stores an electronic medical record.

[2199] 7. Information on specialized medical institutions

[2200] The server will select an internal medicine clinic based on the electronic medical records and diagnosis results, and will also recommend a clinic that can provide mental care, taking into consideration Taro's concerns.

[2201] The server sends the medical institution information to the terminal and displays it to Taro.

[2202] Taro follows the instructions and makes a reservation.

[2203] 8. AI medical record handover

[2204] The server sends the electronic medical record to the clinic where the appointment is completed.

[2205] The medical institution's terminal receives the electronic medical record and prepares for treatment.

[2206] In this way, incorporating an emotion engine makes it possible to provide a more personalized medical experience by responding to the user's emotional state in a more detailed manner.

[2207] The processing flow will be explained below.

[2208] Step 1:

[2209] Users launch the smartphone application and enter their symptoms by text or voice, for example, "I have a sore throat and a fever of 37.5 degrees."

[2210] Step 2:

[2211] The device receives the user's input information and simultaneously activates the emotion engine. The emotion engine analyzes the user's emotional state from the text and voice data entered. For example, it analyzes "anxiety" or "stress" from the words used and tone of voice when entering information.

[2212] Step 3:

[2213] The terminal transmits the analyzed emotion information and the symptom data of the user to the server.

[2214] Step 4:

[2215] The server analyzes the received symptom data and emotional information, passing the text data to a natural language processing (NLP) module to extract keywords such as "sore throat" and "fever," and then applies an initial diagnostic algorithm.

[2216] Step 5:

[2217] The server generates an initial diagnosis, for example, "suspected mild cold."

[2218] Step 6:

[2219] The server automatically generates additional questions taking into account emotional information. If the user is feeling anxious, the server softens the questions or provides detailed, easy-to-understand explanations. For example, it generates questions in the form of "Don't worry. Do you also have a cough or headache?"

[2220] Step 7:

[2221] The terminal displays the additional questions sent from the server to the user.

[2222] Step 8:

[2223] The user enters an answer to the follow-up question, for example, "Yes, I have a slight cough."

[2224] Step 9:

[2225] The terminal transmits the user's response data to the server.

[2226] Step 10:

[2227] The server re-analyzes the additional responses and makes a final diagnosis, for example, a definitive diagnosis of "mild cold."

[2228] Step 11:

[2229] The server automatically generates an electronic medical record based on the user's symptoms, diagnosis results, and emotional information, and securely stores that information in a database.

[2230] Step 12:

[2231] The server selects medical institutions suitable for the user's area based on the generated electronic medical record and diagnosis results. Based on the emotional information, the server also provides additional information, such as clinics that can provide mental health care.

[2232] Step 13:

[2233] The server sends information about the selected medical institution to the terminal and provides the user with guidance, such as "The nearest internal medicine clinic is Hospital A. You can also receive mental health care there."

[2234] Step 14:

[2235] The user selects a medical institution based on the guidance and makes an appointment for a consultation.

[2236] Step 15:

[2237] The server securely transmits the user's electronic medical record and emotional information to the medical institution where the user has completed an appointment.

[2238] Step 16:

[2239] The medical institution's terminal receives the electronic medical record and emotional information sent from the server and prepares for treatment, ensuring smooth treatment when the patient arrives.

[2240] By going through these steps, users can receive prompt and appropriate medical services, and medical institutions can obtain detailed information in advance, resulting in more efficient medical treatment.In addition, the emotion engine enables flexible responses that take into account the user's psychological state.

[2241] Example 2

[2242] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2243] While conventional diagnostic systems can analyze a user's medical information and provide a diagnosis, they lack the ability to adjust the diagnostic process to take into account the user's emotional state, which can lead to users feeling stressed or anxious during the diagnosis process, resulting in a suboptimal medical experience.

[2244] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for a user to input medical information, a means for analyzing the input information, a means for generating an initial diagnosis based on the analysis results, a means for automatically generating additional questions, a means for recognizing the user's emotional state, a means for adjusting the diagnostic process based on the emotional state, a means for making a final diagnosis based on the user's answers, a means for generating an electronic medical record based on the final diagnosis result, a means for saving the generated electronic medical record and the diagnostic result, a means for guiding the user to an appropriate medical institution, and a means for transmitting the electronic medical record to the medical institution. This enables a detailed medical experience tailored to the user's emotional state, and more personalized medical care can be provided.

[2245] The term "user" refers to a person who uses this medical diagnostic system to input symptom information and the like.

[2246] "Medical information" refers to data entered by users regarding symptoms and health conditions.

[2247] "Emotional state" refers to the user's psychological reactions and feelings, including anxiety and stress about things.

[2248] "Means of analysis" refers to the techniques and algorithms used to process and analyze input data and extract meaningful information.

[2249] "Initial diagnosis result" refers to the first predicted diagnosis result obtained based on the input medical information.

[2250] "Means for automatically generating follow-up questions" refers to a technology or process that automatically generates follow-up questions to gather more detailed information based on the results of the initial diagnosis.

[2251] "Emotion engine" refers to the part of the system that includes the technology to recognize and analyze the user's emotional state from input data.

[2252] "Means for adjusting the diagnostic process" refers to technology for appropriately changing the diagnostic process and questions asked based on the user's emotional state.

[2253] "Final diagnosis" refers to a definitive diagnosis result obtained by analyzing all data, including the user's additional responses.

[2254] "Electronic Medical Record" means a medical record that stores a user's medical condition, diagnosis, and related information in digital form.

[2255] "Medical institution" refers to a facility such as a hospital or clinic that provides medical examinations and treatment.

[2256] "Natural language processing technology" refers to technology that allows computers to analyze, understand, and generate human language.

[2257] A "diagnostic algorithm" refers to a calculation procedure or method for making a diagnosis based on medical information.

[2258] A "generative AI model" refers to a model that uses artificial intelligence technology to generate new data and information.

[2259] The present invention provides a system that allows users to input medical information, analyzes that information, and provides diagnostic results. It also incorporates an emotion engine that recognizes the user's emotional state and adjusts the diagnostic process based on that information, thereby providing more appropriate and personalized medical treatment.

[2260] This system can be implemented using the following hardware and software. The hardware includes a smartphone or computer terminal for users to input medical information, and a server for analyzing data and generating diagnostic results. The software includes an AI chatbot app, an emotion engine, natural language processing (NLP) technology, and a diagnostic algorithm.

[2261] The specific system configuration and operation are as follows.

[2262] 1. User symptom input

[2263] Users use their smartphones or computers to input medical information into the AI ​​chatbot app, for example, "I have a sore throat and a slight fever."

[2264] 2. Recognizing emotional states

[2265] The device analyzes the user's input text (or voice) using an emotion engine, which uses NLP techniques and emotion analysis models to assess the user's emotional state, for example recognizing that the user is feeling anxious.

[2266] 3. Symptom analysis

[2267] The server uses NLP technology to analyze the symptom information and emotional state data received from the device. Specifically, it extracts keywords such as "sore throat" and "fever" and also analyzes the emotional information of "anxiety." This analysis uses a generative AI model and existing medical databases (e.g., Medline).

[2268] 4. Initial diagnosis and further questions

[2269] The server generates an initial diagnosis based on the analysis results. If the initial diagnosis is uncertain, the server automatically generates additional questions, such as "Do you have any other symptoms such as a cough or headache?" The questions are flexibly adjusted according to the patient's emotional state.

[2270] 5. Processing the User's Answers

[2271] The user answers the additional questions displayed on the terminal, for example, by typing "Yes, I have a slight cough."

[2272] 6. Final diagnosis and generation of electronic medical record

[2273] The server reanalyzes the user's additional answers and makes a final diagnosis, such as a "mild cold." It also generates and securely stores an electronic medical record based on the diagnosis.

[2274] 7. Medical Institution Information

[2275] The server selects a medical institution suitable for the user's area based on the generated medical record and final diagnosis. Taking into account the analysis results of the emotion engine, it also considers medical institutions that can provide psychological counseling and mental care. Information on appropriate medical institutions is sent to the terminal and directed to the user.

[2276] 8. AI medical record handover

[2277] The server securely transmits the electronic medical record to the medical institution where the user has made a reservation. The medical institution's terminal prepares for the medical treatment based on the received electronic medical record.

[2278] Specific examples

[2279] As an example, consider a case where a user (Taro) is experiencing cold-like symptoms and uses an AI chatbot app to get a diagnosis.

[2280] 1. User symptom input

[2281] Taro launches the app and types in, "I have a sore throat and a slight fever."

[2282] 2. Recognizing emotional states

[2283] The device analyzes the information Taro has entered and determines that he is feeling anxious.

[2284] 3. Symptom analysis

[2285] The server analyzes the received data using NLP technology and extracts keywords such as "sore throat," "fever," and "anxiety."

[2286] 4. Initial diagnosis and further questions

[2287] The initial diagnosis is "suspected cold," and a detailed follow-up question is automatically generated: "Do you have any other coughs or headaches?"

[2288] I'll present an additional question to Taro.

[2289] 5. Processing the User's Answers

[2290] Taro replies, "Yes, I have a slight cough."

[2291] 6. Final diagnosis and generation of electronic medical record

[2292] The server reanalyzes the additional responses and diagnoses the patient as having a mild cold. An electronic medical record is generated based on the diagnosis and stored securely.

[2293] 7. Medical Institution Information

[2294] Based on the electronic medical records and diagnosis results, the server will select an internal medicine clinic and also recommend a clinic that can provide mental care, taking into consideration Taro's anxiety.

[2295] Provide Taro with information about medical institutions.

[2296] 8. AI medical record handover

[2297] The server sends the medical record to the clinic where the reservation has been completed, and the medical institution prepares for treatment based on the received medical record.

[2298] As described above, the system of the present invention provides a detailed medical experience that is tailored to the user's emotional state, realizing personalized medical services.

[2299] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2300] Step 1: User symptom input

[2301] Users use their smartphones or computers to input medical information into the AI ​​chatbot app.

[2302] Example: "I have a sore throat and a slight fever."

[2303] Input: User's symptom information

[2304] Output: User input data stored on the device

[2305] Specific operation: Enter your symptoms into the app's input form and press the send button, and the data will be saved on your device.

[2306] Step 2: Recognizing your emotional state

[2307] The terminal analyzes the user's input text using an emotion engine.

[2308] The emotion engine uses NLP techniques and generative AI models to recognize emotions such as stress and anxiety.

[2309] Input: Text data entered by the user

[2310] Output: Emotional state (e.g., "anxiety")

[2311] Specific operation: The emotion engine analyzes the text and generates emotion tags. These tags are sent to the server.

[2312] Step 3: Symptom analysis

[2313] The server uses NLP technology to analyze the symptom information and emotional state data received from the device.

[2314] Keywords such as "sore throat" and "fever" are extracted, and analysis is performed including "anxiety." The generative AI model and medical databases (e.g., Medline) are referenced.

[2315] Input: Symptom information, emotional state data

[2316] Output: Initial diagnosis (e.g., "Suspected cold")

[2317] How it works: The NLP system extracts keywords, and the generative AI model references the medical database to generate an initial diagnosis.

[2318] Step 4: Initial diagnosis and further questions

[2319] The server generates an initial diagnosis based on the analysis results.

[2320] If the initial diagnosis is uncertain, a generative AI model is used to automatically generate follow-up questions, which are tailored based on the patient's emotional state.

[2321] Input: Analysis results (initial diagnosis)

[2322] Output: Initial diagnostic results and follow-up questions

[2323] Specific operation: The server performs an initial diagnosis, generates additional questions (e.g., "Do you have any other coughs or headaches?"), and sends the results to the device.

[2324] Step 5: Processing the user's answers

[2325] The user answers the additional questions displayed on the terminal.

[2326] For example, respond, "Yes, I have a slight cough."

[2327] Input: User's additional answer

[2328] Output: User response data saved on the device

[2329] Specific operation: When the user enters their answer into the app and presses the submit button, the data is saved on the device.

[2330] Step 6: Final diagnosis and electronic medical rec...

Claims

1. a means for a user to input medical information; means for analyzing input information; means for generating an initial diagnosis based on the analysis results; a means for automatically generating follow-up questions; means for making a final diagnosis based on the user's responses; means for generating an electronic medical record based on the final diagnosis; a means for storing the generated electronic medical record and diagnostic results; A means for guiding the user to an appropriate medical institution; The system includes a means for transmitting electronic medical records to a medical institution.

2. means for updating the electronic medical record based on the user's responses; The system of claim 1 further comprising means for automatically suggesting medical information associated with an updated electronic medical record.

3. A means for analyzing user input information using natural language processing technology; 10. The system of claim 1, further comprising means for applying a diagnostic algorithm to make an initial diagnosis and a final diagnosis.

Images